From 9924cb05e2d3ba4b1984e0d0aea4df7541837c56 Mon Sep 17 00:00:00 2001
From: Stefan Schneider <28340802+stefanbschneider@users.noreply.github.com>
Date: Sun, 17 Nov 2024 22:12:27 +0100
Subject: [PATCH] Unwrap gym env inside Ray wrapper

---
 examples/demo.ipynb                |   6 +-
 examples/rllib.ipynb               | 281 ++++++++++-------------------
 mobile_env/core/base.py            |   2 +-
 mobile_env/wrappers/multi_agent.py |  11 +-
 tests/requirements.txt             |   4 +-
 5 files changed, 113 insertions(+), 191 deletions(-)

diff --git a/examples/demo.ipynb b/examples/demo.ipynb
index 9a5d2df..89d1f3b 100644
--- a/examples/demo.ipynb
+++ b/examples/demo.ipynb
@@ -43,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "collapsed": false,
     "jupyter": {
@@ -89,7 +89,7 @@
    ],
    "source": [
     "# installation via PyPI\n",
-    "!pip install -U mobile-env"
+    "%pip install -U mobile-env"
    ]
   },
   {
@@ -500,7 +500,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
diff --git a/examples/rllib.ipynb b/examples/rllib.ipynb
index 49d16a1..98434dd 100644
--- a/examples/rllib.ipynb
+++ b/examples/rllib.ipynb
@@ -72,14 +72,14 @@
      "output_type": "stream",
      "text": [
       "Requirement already satisfied: mobile-env in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (2.0.3)\n",
-      "Collecting gymnasium<1.0.0 (from mobile-env)\n",
-      "  Using cached gymnasium-0.29.1-py3-none-any.whl.metadata (10 kB)\n",
+      "Requirement already satisfied: gymnasium<1.0.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (0.28.1)\n",
       "Requirement already satisfied: matplotlib in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (3.9.2)\n",
       "Requirement already satisfied: numpy in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (1.26.4)\n",
       "Requirement already satisfied: pandas in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (2.2.3)\n",
       "Requirement already satisfied: pygame in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (2.6.1)\n",
       "Requirement already satisfied: shapely in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (2.0.6)\n",
       "Requirement already satisfied: svgpath2mpl in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from mobile-env) (1.0.0)\n",
+      "Requirement already satisfied: jax-jumpy>=1.0.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium<1.0.0->mobile-env) (1.0.0)\n",
       "Requirement already satisfied: cloudpickle>=1.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium<1.0.0->mobile-env) (3.1.0)\n",
       "Requirement already satisfied: typing-extensions>=4.3.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium<1.0.0->mobile-env) (4.12.2)\n",
       "Requirement already satisfied: farama-notifications>=0.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium<1.0.0->mobile-env) (0.0.4)\n",
@@ -94,46 +94,36 @@
       "Requirement already satisfied: pytz>=2020.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->mobile-env) (2024.2)\n",
       "Requirement already satisfied: tzdata>=2022.7 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->mobile-env) (2024.2)\n",
       "Requirement already satisfied: six>=1.5 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from python-dateutil>=2.7->matplotlib->mobile-env) (1.16.0)\n",
-      "Using cached gymnasium-0.29.1-py3-none-any.whl (953 kB)\n",
-      "Installing collected packages: gymnasium\n",
-      "  Attempting uninstall: gymnasium\n",
-      "    Found existing installation: gymnasium 1.0.0\n",
-      "    Uninstalling gymnasium-1.0.0:\n",
-      "      Successfully uninstalled gymnasium-1.0.0\n",
-      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-      "stable-baselines3 2.0.0 requires gymnasium==0.28.1, but you have gymnasium 0.29.1 which is incompatible.\n",
-      "sb3-contrib 2.4.0a11 requires stable-baselines3<3.0,>=2.4.0a11, but you have stable-baselines3 2.0.0 which is incompatible.\u001b[0m\u001b[31m\n",
-      "\u001b[0mSuccessfully installed gymnasium-0.29.1\n",
       "Note: you may need to restart the kernel to use updated packages.\n",
-      "Requirement already satisfied: ray==2.39.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (2.39.0)\n",
+      "Requirement already satisfied: ray==2.38.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (2.38.0)\n",
       "Requirement already satisfied: torch in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (2.5.1)\n",
       "Requirement already satisfied: tensorboard in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (2.18.0)\n",
-      "Requirement already satisfied: click>=7.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (8.1.7)\n",
-      "Requirement already satisfied: filelock in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (3.16.1)\n",
-      "Requirement already satisfied: jsonschema in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (4.23.0)\n",
-      "Requirement already satisfied: msgpack<2.0.0,>=1.0.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (1.1.0)\n",
-      "Requirement already satisfied: packaging in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (24.1)\n",
-      "Requirement already satisfied: protobuf!=3.19.5,>=3.15.3 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (5.28.3)\n",
-      "Requirement already satisfied: pyyaml in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (6.0.2)\n",
-      "Requirement already satisfied: aiosignal in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (1.3.1)\n",
-      "Requirement already satisfied: frozenlist in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (1.5.0)\n",
-      "Requirement already satisfied: requests in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.39.0->ray[rllib]==2.39.0) (2.32.3)\n",
-      "Requirement already satisfied: pandas in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (2.2.3)\n",
-      "Requirement already satisfied: tensorboardX>=1.9 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (2.6.2.2)\n",
-      "Requirement already satisfied: pyarrow>=6.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (18.0.0)\n",
-      "Requirement already satisfied: fsspec in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (2024.10.0)\n",
-      "Requirement already satisfied: dm-tree in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (0.1.8)\n",
-      "Collecting gymnasium==1.0.0 (from ray[rllib]==2.39.0)\n",
-      "  Using cached gymnasium-1.0.0-py3-none-any.whl.metadata (9.5 kB)\n",
-      "Requirement already satisfied: lz4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (4.3.3)\n",
-      "Requirement already satisfied: scikit-image in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (0.24.0)\n",
-      "Requirement already satisfied: scipy in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (1.14.1)\n",
-      "Requirement already satisfied: typer in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (0.12.5)\n",
-      "Requirement already satisfied: rich in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.39.0) (13.9.4)\n",
-      "Requirement already satisfied: numpy>=1.21.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==1.0.0->ray[rllib]==2.39.0) (1.26.4)\n",
-      "Requirement already satisfied: cloudpickle>=1.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==1.0.0->ray[rllib]==2.39.0) (3.1.0)\n",
-      "Requirement already satisfied: typing-extensions>=4.3.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==1.0.0->ray[rllib]==2.39.0) (4.12.2)\n",
-      "Requirement already satisfied: farama-notifications>=0.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==1.0.0->ray[rllib]==2.39.0) (0.0.4)\n",
+      "Requirement already satisfied: click>=7.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (8.1.7)\n",
+      "Requirement already satisfied: filelock in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (3.16.1)\n",
+      "Requirement already satisfied: jsonschema in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (4.23.0)\n",
+      "Requirement already satisfied: msgpack<2.0.0,>=1.0.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (1.1.0)\n",
+      "Requirement already satisfied: packaging in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (24.1)\n",
+      "Requirement already satisfied: protobuf!=3.19.5,>=3.15.3 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (5.28.3)\n",
+      "Requirement already satisfied: pyyaml in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (6.0.2)\n",
+      "Requirement already satisfied: aiosignal in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (1.3.1)\n",
+      "Requirement already satisfied: frozenlist in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (1.5.0)\n",
+      "Requirement already satisfied: requests in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray==2.38.0->ray[rllib]==2.38.0) (2.32.3)\n",
+      "Requirement already satisfied: pandas in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (2.2.3)\n",
+      "Requirement already satisfied: tensorboardX>=1.9 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (2.6.2.2)\n",
+      "Requirement already satisfied: pyarrow>=6.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (18.0.0)\n",
+      "Requirement already satisfied: fsspec in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (2024.10.0)\n",
+      "Requirement already satisfied: dm-tree in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (0.1.8)\n",
+      "Requirement already satisfied: gymnasium==0.28.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (0.28.1)\n",
+      "Requirement already satisfied: lz4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (4.3.3)\n",
+      "Requirement already satisfied: scikit-image in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (0.24.0)\n",
+      "Requirement already satisfied: scipy in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (1.14.1)\n",
+      "Requirement already satisfied: typer in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (0.12.5)\n",
+      "Requirement already satisfied: rich in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from ray[rllib]==2.38.0) (13.9.4)\n",
+      "Requirement already satisfied: numpy>=1.21.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==0.28.1->ray[rllib]==2.38.0) (1.26.4)\n",
+      "Requirement already satisfied: jax-jumpy>=1.0.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==0.28.1->ray[rllib]==2.38.0) (1.0.0)\n",
+      "Requirement already satisfied: cloudpickle>=1.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==0.28.1->ray[rllib]==2.38.0) (3.1.0)\n",
+      "Requirement already satisfied: typing-extensions>=4.3.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==0.28.1->ray[rllib]==2.38.0) (4.12.2)\n",
+      "Requirement already satisfied: farama-notifications>=0.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from gymnasium==0.28.1->ray[rllib]==2.38.0) (0.0.4)\n",
       "Requirement already satisfied: networkx in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from torch) (3.4.2)\n",
       "Requirement already satisfied: jinja2 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from torch) (3.1.4)\n",
       "Requirement already satisfied: setuptools in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from torch) (75.3.0)\n",
@@ -146,36 +136,25 @@
       "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from tensorboard) (0.7.2)\n",
       "Requirement already satisfied: werkzeug>=1.0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from tensorboard) (3.1.1)\n",
       "Requirement already satisfied: MarkupSafe>=2.1.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from werkzeug>=1.0.1->tensorboard) (3.0.2)\n",
-      "Requirement already satisfied: attrs>=22.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.39.0->ray[rllib]==2.39.0) (24.2.0)\n",
-      "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.39.0->ray[rllib]==2.39.0) (2024.10.1)\n",
-      "Requirement already satisfied: referencing>=0.28.4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.39.0->ray[rllib]==2.39.0) (0.35.1)\n",
-      "Requirement already satisfied: rpds-py>=0.7.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.39.0->ray[rllib]==2.39.0) (0.20.1)\n",
-      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.39.0) (2.9.0.post0)\n",
-      "Requirement already satisfied: pytz>=2020.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.39.0) (2024.2)\n",
-      "Requirement already satisfied: tzdata>=2022.7 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.39.0) (2024.2)\n",
-      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.39.0->ray[rllib]==2.39.0) (3.4.0)\n",
-      "Requirement already satisfied: idna<4,>=2.5 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.39.0->ray[rllib]==2.39.0) (3.10)\n",
-      "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.39.0->ray[rllib]==2.39.0) (2.2.3)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.39.0->ray[rllib]==2.39.0) (2024.8.30)\n",
-      "Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from rich->ray[rllib]==2.39.0) (3.0.0)\n",
-      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from rich->ray[rllib]==2.39.0) (2.18.0)\n",
-      "Requirement already satisfied: pillow>=9.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.39.0) (11.0.0)\n",
-      "Requirement already satisfied: imageio>=2.33 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.39.0) (2.36.0)\n",
-      "Requirement already satisfied: tifffile>=2022.8.12 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.39.0) (2024.9.20)\n",
-      "Requirement already satisfied: lazy-loader>=0.4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.39.0) (0.4)\n",
-      "Requirement already satisfied: shellingham>=1.3.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from typer->ray[rllib]==2.39.0) (1.5.4)\n",
-      "Requirement already satisfied: mdurl~=0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich->ray[rllib]==2.39.0) (0.1.2)\n",
-      "Using cached gymnasium-1.0.0-py3-none-any.whl (958 kB)\n",
-      "Installing collected packages: gymnasium\n",
-      "  Attempting uninstall: gymnasium\n",
-      "    Found existing installation: gymnasium 0.29.1\n",
-      "    Uninstalling gymnasium-0.29.1:\n",
-      "      Successfully uninstalled gymnasium-0.29.1\n",
-      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-      "stable-baselines3 2.0.0 requires gymnasium==0.28.1, but you have gymnasium 1.0.0 which is incompatible.\n",
-      "mobile-env 2.0.3 requires gymnasium<1.0.0, but you have gymnasium 1.0.0 which is incompatible.\n",
-      "sb3-contrib 2.4.0a11 requires stable-baselines3<3.0,>=2.4.0a11, but you have stable-baselines3 2.0.0 which is incompatible.\u001b[0m\u001b[31m\n",
-      "\u001b[0mSuccessfully installed gymnasium-1.0.0\n",
+      "Requirement already satisfied: attrs>=22.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.38.0->ray[rllib]==2.38.0) (24.2.0)\n",
+      "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.38.0->ray[rllib]==2.38.0) (2024.10.1)\n",
+      "Requirement already satisfied: referencing>=0.28.4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.38.0->ray[rllib]==2.38.0) (0.35.1)\n",
+      "Requirement already satisfied: rpds-py>=0.7.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from jsonschema->ray==2.38.0->ray[rllib]==2.38.0) (0.20.1)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.38.0) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.38.0) (2024.2)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from pandas->ray[rllib]==2.38.0) (2024.2)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.38.0->ray[rllib]==2.38.0) (3.4.0)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.38.0->ray[rllib]==2.38.0) (3.10)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.38.0->ray[rllib]==2.38.0) (2.2.3)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from requests->ray==2.38.0->ray[rllib]==2.38.0) (2024.8.30)\n",
+      "Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from rich->ray[rllib]==2.38.0) (3.0.0)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from rich->ray[rllib]==2.38.0) (2.18.0)\n",
+      "Requirement already satisfied: pillow>=9.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.38.0) (11.0.0)\n",
+      "Requirement already satisfied: imageio>=2.33 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.38.0) (2.36.0)\n",
+      "Requirement already satisfied: tifffile>=2022.8.12 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.38.0) (2024.9.20)\n",
+      "Requirement already satisfied: lazy-loader>=0.4 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from scikit-image->ray[rllib]==2.38.0) (0.4)\n",
+      "Requirement already satisfied: shellingham>=1.3.0 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from typer->ray[rllib]==2.38.0) (1.5.4)\n",
+      "Requirement already satisfied: mdurl~=0.1 in /Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich->ray[rllib]==2.38.0) (0.1.2)\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
@@ -184,7 +163,7 @@
     "# install mobile-env\n",
     "%pip install -U mobile-env\n",
     "# install ray RLlib\n",
-    "%pip install \"ray[rllib]==2.39.0\" torch tensorboard"
+    "%pip install \"ray[rllib]==2.38.0\" torch tensorboard"
    ]
   },
   {
@@ -239,13 +218,13 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-11-16 21:13:25,398\tINFO worker.py:1819 -- Started a local Ray instance.\n"
+      "2024-11-17 22:09:07,509\tINFO worker.py:1816 -- Started a local Ray instance.\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2c403bcd8a354cd9b9ad13c8946c28be",
+       "model_id": "528c7fce5b4648f99f61495a3af85f3c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -273,7 +252,7 @@
        "    </tr>\n",
        "    <tr>\n",
        "        <td style=\"text-align: left\"><b>Ray version:</b></td>\n",
-       "        <td style=\"text-align: left\"><b>2.39.0</b></td>\n",
+       "        <td style=\"text-align: left\"><b>2.38.0</b></td>\n",
        "    </tr>\n",
        "    \n",
        "</table>\n",
@@ -282,7 +261,7 @@
        "</div>\n"
       ],
       "text/plain": [
-       "RayContext(dashboard_url='', python_version='3.12.6', ray_version='2.39.0', ray_commit='5a6c33536df3f6ed5e987a169b82739bb7e3d80e')"
+       "RayContext(dashboard_url='', python_version='3.12.6', ray_version='2.38.0', ray_commit='385ee466260ef3cd218d5e372aef5d39338b7b94')"
       ]
      },
      "execution_count": 3,
@@ -319,60 +298,30 @@
        "      <h3>Tune Status</h3>\n",
        "      <table>\n",
        "<tbody>\n",
-       "<tr><td>Current time:</td><td>2024-11-16 21:13:35</td></tr>\n",
-       "<tr><td>Running for: </td><td>00:00:07.50        </td></tr>\n",
-       "<tr><td>Memory:      </td><td>18.1/32.0 GiB      </td></tr>\n",
+       "<tr><td>Current time:</td><td>2024-11-17 22:09:39</td></tr>\n",
+       "<tr><td>Running for: </td><td>00:00:29.46        </td></tr>\n",
+       "<tr><td>Memory:      </td><td>18.8/32.0 GiB      </td></tr>\n",
        "</tbody>\n",
        "</table>\n",
        "    </div>\n",
        "    <div class=\"vDivider\"></div>\n",
        "    <div class=\"systemInfo\">\n",
        "      <h3>System Info</h3>\n",
-       "      Using FIFO scheduling algorithm.<br>Logical resource usage: 0/2 CPUs, 0/0 GPUs\n",
+       "      Using FIFO scheduling algorithm.<br>Logical resource usage: 2.0/2 CPUs, 0/0 GPUs\n",
        "    </div>\n",
-       "    <div class=\"vDivider\"></div>\n",
-       "<div class=\"messages\">\n",
-       "  <h3>Messages</h3>\n",
-       "  \n",
-       "  \n",
-       "  Number of errored trials: 1<br><table>\n",
-       "<thead>\n",
-       "<tr><th>Trial name                        </th><th style=\"text-align: right;\">  # failures</th><th>error file                                                                                                                                                                                 </th></tr>\n",
-       "</thead>\n",
-       "<tbody>\n",
-       "<tr><td>PPO_mobile-small-ma-v0_3dabb_00000</td><td style=\"text-align: right;\">           1</td><td>/tmp/ray/session_2024-11-16_21-13-23_564923_98212/artifacts/2024-11-16_21-13-27/PPO_2024-11-16_21-13-27/driver_artifacts/PPO_mobile-small-ma-v0_3dabb_00000_0_2024-11-16_21-13-27/error.txt</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n",
-       "</div>\n",
-       "<style>\n",
-       ".messages {\n",
-       "  color: var(--jp-ui-font-color1);\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  padding-left: 1em;\n",
-       "  overflow-y: auto;\n",
-       "}\n",
-       ".messages h3 {\n",
-       "  font-weight: bold;\n",
-       "}\n",
-       ".vDivider {\n",
-       "  border-left-width: var(--jp-border-width);\n",
-       "  border-left-color: var(--jp-border-color0);\n",
-       "  border-left-style: solid;\n",
-       "  margin: 0.5em 1em 0.5em 1em;\n",
-       "}\n",
-       "</style>\n",
-       "\n",
+       "    \n",
        "  </div>\n",
        "  <div class=\"hDivider\"></div>\n",
        "  <div class=\"trialStatus\">\n",
        "    <h3>Trial Status</h3>\n",
        "    <table>\n",
        "<thead>\n",
-       "<tr><th>Trial name                        </th><th>status  </th><th>loc  </th></tr>\n",
+       "<tr><th>Trial name                        </th><th>status    </th><th>loc            </th><th style=\"text-align: right;\">  iter</th><th style=\"text-align: right;\">  total time (s)</th><th style=\"text-align: right;\">  ts</th><th style=\"text-align: right;\">  num_healthy_workers</th><th style=\"text-align: right;\">  num_in_flight_async_\n",
+       "sample_reqs</th><th style=\"text-align: right;\">  num_remote_worker_re\n",
+       "starts</th></tr>\n",
        "</thead>\n",
        "<tbody>\n",
-       "<tr><td>PPO_mobile-small-ma-v0_3dabb_00000</td><td>ERROR   </td><td>     </td></tr>\n",
+       "<tr><td>PPO_mobile-small-ma-v0_3029c_00000</td><td>TERMINATED</td><td>127.0.0.1:19039</td><td style=\"text-align: right;\">     1</td><td style=\"text-align: right;\">         20.8382</td><td style=\"text-align: right;\">4000</td><td style=\"text-align: right;\">                    1</td><td style=\"text-align: right;\">0</td><td style=\"text-align: right;\">0</td></tr>\n",
        "</tbody>\n",
        "</table>\n",
        "  </div>\n",
@@ -419,61 +368,8 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-11-16 21:13:27,631\tWARNING ppo.py:305 -- You are running PPO on the new API stack! This is the new default behavior for this algorithm. If you don't want to use the new API stack, set `config.api_stack(enable_rl_module_and_learner=False,enable_env_runner_and_connector_v2=False)`. For a detailed migration guide, see here: https://docs.ray.io/en/master/rllib/new-api-stack-migration-guide.html\n",
-      "2024-11-16 21:13:27,632\tWARNING ppo.py:305 -- You are running PPO on the new API stack! This is the new default behavior for this algorithm. If you don't want to use the new API stack, set `config.api_stack(enable_rl_module_and_learner=False,enable_env_runner_and_connector_v2=False)`. For a detailed migration guide, see here: https://docs.ray.io/en/master/rllib/new-api-stack-migration-guide.html\n",
-      "2024-11-16 21:13:35,053\tERROR tune_controller.py:1331 -- Trial task failed for trial PPO_mobile-small-ma-v0_3dabb_00000\n",
-      "Traceback (most recent call last):\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/air/execution/_internal/event_manager.py\", line 110, in resolve_future\n",
-      "    result = ray.get(future)\n",
-      "             ^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/_private/auto_init_hook.py\", line 21, in auto_init_wrapper\n",
-      "    return fn(*args, **kwargs)\n",
-      "           ^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/_private/client_mode_hook.py\", line 103, in wrapper\n",
-      "    return func(*args, **kwargs)\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/_private/worker.py\", line 2753, in get\n",
-      "    values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout)\n",
-      "                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/_private/worker.py\", line 906, in get_objects\n",
-      "    raise value\n",
-      "ray.exceptions.ActorDiedError: The actor died because of an error raised in its creation task, \u001b[36mray::PPO.__init__()\u001b[39m (pid=98290, ip=127.0.0.1, actor_id=4f983bb461cc69c378744e1a01000000, repr=PPO)\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/algorithms/algorithm.py\", line 583, in __init__\n",
-      "    super().__init__(\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/tune/trainable/trainable.py\", line 158, in __init__\n",
-      "    self.setup(copy.deepcopy(self.config))\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/algorithms/algorithm.py\", line 669, in setup\n",
-      "    self.env_runner_group = EnvRunnerGroup(\n",
-      "                            ^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/env/env_runner_group.py\", line 194, in __init__\n",
-      "    self._setup(\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/env/env_runner_group.py\", line 285, in _setup\n",
-      "    self._local_env_runner = self._make_worker(\n",
-      "                             ^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/env/env_runner_group.py\", line 1180, in _make_worker\n",
-      "    worker = cls(\n",
-      "             ^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/env/multi_agent_env_runner.py\", line 90, in __init__\n",
-      "    self.make_env()\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/env/multi_agent_env_runner.py\", line 854, in make_env\n",
-      "    self.env: MultiAgentEnv = gym.make(\"rllib-multi-agent-env-v0\")\n",
-      "                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/gymnasium/envs/registration.py\", line 740, in make\n",
-      "    env = env_creator(**env_spec_kwargs)\n",
-      "          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"/var/folders/1n/twp7by_x5t30fzp0f2md9j_h0000gn/T/ipykernel_98212/428465780.py\", line 14, in register\n",
-      "  File \"/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/mobile_env/wrappers/multi_agent.py\", line 19, in __init__\n",
-      "    self.max_episode_steps = self.env.EP_MAX_TIME\n",
-      "                             ^^^^^^^^^^^^^^^^^^^^\n",
-      "AttributeError: 'OrderEnforcing' object has no attribute 'EP_MAX_TIME'\n",
-      "2024-11-16 21:13:35,081\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '/Users/stefanshschneider/ray_results/PPO_2024-11-16_21-13-27' in 0.0194s.\n",
-      "2024-11-16 21:13:35,085\tERROR tune.py:1037 -- Trials did not complete: [PPO_mobile-small-ma-v0_3dabb_00000]\n",
-      "2024-11-16 21:13:35,085\tINFO tune.py:1041 -- Total run time: 7.63 seconds (7.48 seconds for the tuning loop).\n",
-      "2024-11-16 21:13:35,088\tWARNING experiment_analysis.py:180 -- Failed to fetch metrics for 1 trial(s):\n",
-      "- PPO_mobile-small-ma-v0_3dabb_00000: FileNotFoundError('Could not fetch metrics for PPO_mobile-small-ma-v0_3dabb_00000: both result.json and progress.csv were not found at /Users/stefanshschneider/ray_results/PPO_2024-11-16_21-13-27/PPO_mobile-small-ma-v0_3dabb_00000_0_2024-11-16_21-13-27')\n"
+      "2024-11-17 22:09:39,186\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '/Users/stefanshschneider/ray_results/PPO_2024-11-17_22-09-09' in 0.0187s.\n",
+      "2024-11-17 22:09:39,733\tINFO tune.py:1041 -- Total run time: 30.05 seconds (29.44 seconds for the tuning loop).\n"
      ]
     }
    ],
@@ -532,7 +428,7 @@
     {
      "data": {
       "text/plain": [
-       "Launching TensorBoard..."
+       "Reusing TensorBoard on port 6006 (pid 10623), started 7:29:55 ago. (Use '!kill 10623' to kill it.)"
       ]
      },
      "metadata": {},
@@ -542,11 +438,11 @@
      "data": {
       "text/html": [
        "\n",
-       "      <iframe id=\"tensorboard-frame-3ffd5d37bf668de4\" width=\"100%\" height=\"800\" frameborder=\"0\">\n",
+       "      <iframe id=\"tensorboard-frame-f98bb2ffcc34fa57\" width=\"100%\" height=\"800\" frameborder=\"0\">\n",
        "      </iframe>\n",
        "      <script>\n",
        "        (function() {\n",
-       "          const frame = document.getElementById(\"tensorboard-frame-3ffd5d37bf668de4\");\n",
+       "          const frame = document.getElementById(\"tensorboard-frame-f98bb2ffcc34fa57\");\n",
        "          const url = new URL(\"http://localhost\");\n",
        "          const port = 6006;\n",
        "          if (port) {\n",
@@ -586,16 +482,37 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "ValueError",
-     "evalue": "`path` not provided in call to Algorithm.from_checkpoint()!",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[6], line 5\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;66;03m# load the trained agent from the stored checkpoint\u001b[39;00m\n\u001b[1;32m      4\u001b[0m best_result \u001b[38;5;241m=\u001b[39m result_grid\u001b[38;5;241m.\u001b[39mget_best_result(metric\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mepisode_reward_mean\u001b[39m\u001b[38;5;124m\"\u001b[39m, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 5\u001b[0m ppo \u001b[38;5;241m=\u001b[39m \u001b[43mAlgorithm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_checkpoint\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbest_result\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcheckpoint\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      6\u001b[0m best_result\n",
-      "File \u001b[0;32m~/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/algorithms/algorithm.py:353\u001b[0m, in \u001b[0;36mAlgorithm.from_checkpoint\u001b[0;34m(cls, path, filesystem, policy_ids, policy_mapping_fn, policies_to_train, checkpoint, **kwargs)\u001b[0m\n\u001b[1;32m    351\u001b[0m     path \u001b[38;5;241m=\u001b[39m checkpoint\n\u001b[1;32m    352\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m path \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 353\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    354\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`path` not provided in call to Algorithm.from_checkpoint()!\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    355\u001b[0m     )\n\u001b[1;32m    357\u001b[0m checkpoint_info \u001b[38;5;241m=\u001b[39m get_checkpoint_info(path)\n\u001b[1;32m    359\u001b[0m \u001b[38;5;66;03m# Not possible for (v0.1) (algo class and config information missing\u001b[39;00m\n\u001b[1;32m    360\u001b[0m \u001b[38;5;66;03m# or very hard to retrieve).\u001b[39;00m\n",
-      "\u001b[0;31mValueError\u001b[0m: `path` not provided in call to Algorithm.from_checkpoint()!"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/rllib/algorithms/algorithm.py:568: RayDeprecationWarning: This API is deprecated and may be removed in future Ray releases. You could suppress this warning by setting env variable PYTHONWARNINGS=\"ignore::DeprecationWarning\"\n",
+      "`UnifiedLogger` will be removed in Ray 2.7.\n",
+      "  return UnifiedLogger(config, logdir, loggers=None)\n",
+      "/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/tune/logger/unified.py:53: RayDeprecationWarning: This API is deprecated and may be removed in future Ray releases. You could suppress this warning by setting env variable PYTHONWARNINGS=\"ignore::DeprecationWarning\"\n",
+      "The `JsonLogger interface is deprecated in favor of the `ray.tune.json.JsonLoggerCallback` interface and will be removed in Ray 2.7.\n",
+      "  self._loggers.append(cls(self.config, self.logdir, self.trial))\n",
+      "/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/tune/logger/unified.py:53: RayDeprecationWarning: This API is deprecated and may be removed in future Ray releases. You could suppress this warning by setting env variable PYTHONWARNINGS=\"ignore::DeprecationWarning\"\n",
+      "The `CSVLogger interface is deprecated in favor of the `ray.tune.csv.CSVLoggerCallback` interface and will be removed in Ray 2.7.\n",
+      "  self._loggers.append(cls(self.config, self.logdir, self.trial))\n",
+      "/Users/stefanshschneider/Projects/private/mobile-env/venv/lib/python3.12/site-packages/ray/tune/logger/unified.py:53: RayDeprecationWarning: This API is deprecated and may be removed in future Ray releases. You could suppress this warning by setting env variable PYTHONWARNINGS=\"ignore::DeprecationWarning\"\n",
+      "The `TBXLogger interface is deprecated in favor of the `ray.tune.tensorboardx.TBXLoggerCallback` interface and will be removed in Ray 2.7.\n",
+      "  self._loggers.append(cls(self.config, self.logdir, self.trial))\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Result(\n",
+       "  metrics={'custom_metrics': {}, 'episode_media': {}, 'info': {'learner': {'shared_policy': {'learner_stats': {'allreduce_latency': 0.0, 'grad_gnorm': 1.6213738948992609, 'cur_kl_coeff': 0.2, 'cur_lr': 5.0000000000000016e-05, 'total_loss': 8.009701963493525, 'policy_loss': -0.008299151918210184, 'vf_loss': 8.015849697615185, 'vf_explained_var': 0.04391117921047656, 'kl': 0.01075709559530967, 'entropy': 1.3758156238847477, 'entropy_coeff': 0.0}, 'model': {}, 'custom_metrics': {}, 'num_agent_steps_trained': 127.38853503184713, 'num_grad_updates_lifetime': 2355.5, 'diff_num_grad_updates_vs_sampler_policy': 2354.5}}, 'num_env_steps_sampled': 4000, 'num_env_steps_trained': 4000, 'num_agent_steps_sampled': 20000, 'num_agent_steps_trained': 20000}, 'env_runners': {'episode_reward_max': -2.966881031323917, 'episode_reward_min': -341.7161232310376, 'episode_reward_mean': -187.20572839930978, 'episode_len_mean': 100.0, 'episode_media': {}, 'episodes_timesteps_total': 4000, 'policy_reward_min': {'shared_policy': -90.87986640184575}, 'policy_reward_max': {'shared_policy': 5.369115924522074}, 'policy_reward_mean': {'shared_policy': -37.441145679861954}, 'custom_metrics': {}, 'hist_stats': {'episode_reward': [-341.7161232310376, -210.10479259347105, -280.2208090574522, -172.34659666672397, -296.5657717575985, -166.24725216132202, -199.35735777174065, -223.4849183806289, -68.99070997828451, -203.2493766961578, -161.9034347627089, -193.38030606269552, -156.86632230206808, -171.03194135163199, -197.26961971176652, -161.9014008110669, -226.83900063103283, -258.6117167543199, -245.24433781916883, -212.83897613153187, -156.59672053114303, -2.966881031323917, -163.34609209515062, -139.52202385843694, -243.17107560425902, -219.8687089505345, -131.60110163391084, -91.21862899962417, -141.12357268091293, -180.72687099816667, -205.37555769979545, -290.7562339904011, -265.0984697032583, -78.111949858501, -110.88002408892798, -215.32274560392557, -204.89239800599358, -177.1517175280564, -137.30632788771996, -185.0212705899408], 'episode_lengths': [100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100], 'policy_shared_policy_reward': [-75.97376292526073, -55.70188255003805, -60.550893308217304, -77.62041509910816, -71.86916934841331, -61.208364563366565, -43.95764300794533, -26.365322337227756, -17.14514742354721, -61.42831526138406, -81.2820086104112, -56.1438656055417, -28.647571321033976, -60.10606791263098, -54.04129560783462, -28.46998459838941, -58.63935862437817, -38.51265772682591, -31.494795542965775, -15.229800174164643, -57.69939029964555, -56.38478494383098, -53.38873667085906, -74.83473591625346, -54.25812392700937, -44.17057105155368, -19.38297212981529, -22.447590004221805, -26.243521857159024, -54.002597118572346, -49.776872666641, -15.907262620114796, -41.59078339173041, -26.01765372666303, -66.06478536659144, -44.7113374630515, -57.56318914672269, -65.9855046742508, -29.95556847878577, -25.269318617817902, -17.972544549388882, -16.634077926255628, -1.1939891445548616, -33.74458476009921, 0.554486402014063, -33.37317107660478, -25.131440840330622, -73.22265187712725, -39.667383379228035, -31.854729522867117, -49.74153538512278, -21.663601979990823, -42.115258992611174, -12.433170452541424, -35.94986795244273, -51.45034724820258, -21.758297997171862, -70.93040867938883, -39.3858501581646, -9.855401979767663, -50.179085996540806, -28.91682048666958, -29.42490437855196, -35.749361394617665, -12.596150045687988, -48.081331172853446, -46.08858671548431, -22.48500921886698, -27.52214187663568, -26.85487236779168, -40.91696033389797, -32.070355422912904, -35.07694655718345, -60.58767350859549, -28.617683889176686, -23.995020595096115, -21.563521577307224, -29.586049729379667, -58.298961194779054, -28.45784771450478, -49.45721997211554, -32.90268144820824, -62.45383562328173, -16.52633868230682, -65.49892490512049, -71.07145990097465, -49.41098758754849, -34.475792306276745, -51.08985707055336, -52.563619888966315, -36.88369983919451, -47.66704058098666, -68.95923086892174, -50.133234034866604, -41.60113249519934, -39.73737163503491, -28.7213726557908, -45.426866459826705, -70.64948789620209, -28.303877484677265, -32.689526783126375, -52.707779168618785, -36.674089342453655, -12.455842568861625, -22.06948266808256, -0.7104497026480319, 2.949574050941887, 1.7772407699397685, 5.369115924522074, -12.352362074079611, -30.472901016884194, -18.572605951977753, -10.414256792648992, -47.707620800694606, -56.17870753294515, -7.061947121528968, -15.945812150186653, -20.109767173998147, -64.33200632568912, -32.07249108703408, -66.1029676764273, -37.31577402210522, -70.33536439092276, -35.99671422135832, -33.420255293445585, -52.54951853999192, -24.753011060695616, -10.486785892070325, -54.85546945726677, -77.22392400050968, -35.75755055205849, -37.38447699678598, -15.620989061777475, -44.156791494161794, 1.3187064708729692, -32.87415477472307, -11.948652777664567, -17.685064214342777, -27.841745489820152, -0.8690117430736359, -22.588565771531183, -22.924099865812646, -19.587176439232966, -50.3251253311784, -25.6986052731577, -31.166241667648034, -62.51390549794251, -29.036164018646975, -35.82792166732255, -22.182638146606834, -45.595820524068735, -20.901029548934833, -90.87986640184575, -25.831293432341926, -22.167547792604132, -62.689527022778215, -44.448903389348054, -66.41952210274167, -56.00587973896291, -61.192401736570766, -57.74974644339343, -81.7130380097914, -32.95753905338611, -45.14689942116229, -47.53124677552484, -11.745168471397992, -41.909006615648686, -12.19320012745216, -6.543017606664212, -5.721557037337991, -23.736509907690536, -15.182759852910305, -27.148944241951504, -11.647881561340292, -33.16392852503545, -76.10121889360776, -34.61493725183212, -33.74338739756905, -37.24963733184732, -33.61356472906914, -49.54711600665791, -35.252489128799205, -35.7585491182765, -44.80204034403909, -39.532203408220774, -52.687061815037346, -58.19741846381604, -25.281812661360302, -13.2848811722991, -27.70054341554363, -32.78560653001561, -9.58385479427104, -42.3163114226674, -38.11716535084875, -14.503389789917142, -38.1679669833946, -68.81546866730723, -32.79968835471966, -24.544512392451168, -20.693634192068064]}, 'sampler_perf': {'mean_raw_obs_processing_ms': 0.3864632282099763, 'mean_inference_ms': 0.35320356827144533, 'mean_action_processing_ms': 0.11701424161781819, 'mean_env_wait_ms': 1.281081065926603, 'mean_env_render_ms': 0.0}, 'num_faulty_episodes': 0, 'connector_metrics': {'ObsPreprocessorConnector_ms': 0.002974271774291992, 'StateBufferConnector_ms': 0.0027894973754882812, 'ViewRequirementAgentConnector_ms': 0.11682748794555664}, 'num_episodes': 40, 'episode_return_max': -2.966881031323917, 'episode_return_min': -341.7161232310376, 'episode_return_mean': -187.20572839930978, 'episodes_this_iter': 40}, 'num_healthy_workers': 1, 'num_in_flight_async_sample_reqs': 0, 'num_remote_worker_restarts': 0, 'num_agent_steps_sampled': 20000, 'num_agent_steps_trained': 20000, 'num_env_steps_sampled': 4000, 'num_env_steps_trained': 4000, 'num_env_steps_sampled_this_iter': 4000, 'num_env_steps_trained_this_iter': 4000, 'num_env_steps_sampled_throughput_per_sec': 191.9822989953357, 'num_env_steps_trained_throughput_per_sec': 191.9822989953357, 'num_env_steps_sampled_lifetime': 4000, 'num_agent_steps_sampled_lifetime': 20000, 'num_steps_trained_this_iter': 4000, 'agent_timesteps_total': 20000, 'timers': {'training_iteration_time_ms': 20835.307, 'restore_workers_time_ms': 0.067, 'training_step_time_ms': 20835.163, 'sample_time_ms': 8586.37, 'learn_time_ms': 12246.038, 'learn_throughput': 326.636, 'synch_weights_time_ms': 2.231}, 'counters': {'num_env_steps_sampled': 4000, 'num_env_steps_trained': 4000, 'num_agent_steps_sampled': 20000, 'num_agent_steps_trained': 20000}, 'perf': {'cpu_util_percent': 17.339999999999996, 'ram_util_percent': 58.739999999999995}},\n",
+       "  path='/Users/stefanshschneider/ray_results/PPO_2024-11-17_22-09-09/PPO_mobile-small-ma-v0_3029c_00000_0_2024-11-17_22-09-09',\n",
+       "  filesystem='local',\n",
+       "  checkpoint=Checkpoint(filesystem=local, path=/Users/stefanshschneider/ray_results/PPO_2024-11-17_22-09-09/PPO_mobile-small-ma-v0_3029c_00000_0_2024-11-17_22-09-09/checkpoint_000000)\n",
+       ")"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -609,12 +526,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
diff --git a/mobile_env/core/base.py b/mobile_env/core/base.py
index 4477226..b2ffb68 100644
--- a/mobile_env/core/base.py
+++ b/mobile_env/core/base.py
@@ -202,7 +202,7 @@ def reset(self, *, seed=None, options=None):
             self.rng = np.random.default_rng(self.seed)
 
         # extra options currently not supported
-        if options is not None:
+        if options is not None and options != {}:
             raise NotImplementedError(
                 "Passing extra options on env.reset() is not supported."
             )
diff --git a/mobile_env/wrappers/multi_agent.py b/mobile_env/wrappers/multi_agent.py
index 8a77801..bf01eff 100644
--- a/mobile_env/wrappers/multi_agent.py
+++ b/mobile_env/wrappers/multi_agent.py
@@ -9,11 +9,16 @@
 
 
 class RLlibMAWrapper(MultiAgentEnv):
-    def __init__(self, env: MComCore):
+    def __init__(self, env: gymnasium.Env):
         super().__init__()
 
-        # class wrapps environment object
-        self.env = env
+        # Keep a reference to the mobile-env base environment, which is wrapped by this class.
+        # Remove any gymnasium wrappers first if needed.
+        if isinstance(env, MComCore):
+            self.env: MComCore = env
+        else:
+            assert isinstance(env.unwrapped, MComCore), "The unwrapped env should be a mobile-env."
+            self.env = env.unwrapped
 
         # set max. number of steps for RLlib trainer
         self.max_episode_steps = self.env.EP_MAX_TIME
diff --git a/tests/requirements.txt b/tests/requirements.txt
index 599b04c..8778726 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -6,5 +6,5 @@ pytest
 nbmake
 # Older stable baselines versions do not support gymnasium
 stable-baselines3>=2.0.0
-# Only Ray 2.3+ supports gymnasium
-#ray[rllib]>=2.3.0
+# Only Ray 2.3+ supports gymnasium. Ray 2.39 needs gymnasium 1.0 and isn't fully supported yet.
+#ray[rllib]>=2.3.0, <2.39