Skip to content

camera-based RL with state-reconstruction and object permanence

License

Notifications You must be signed in to change notification settings

jumpers775/lightning

Repository files navigation

Kachow!

"I am lightning" - Lightning McQueen

How This Works

  1. there are two models:
    • State constructor (get environment state from video)
    • control model (generates actions from environment state)
  2. we train a custom CNN (Convolutional Neural Network) + LSTM (long short term memory) hybrid model to reconstruct environment state from states encountered during control model training.
    • The environment state can be directly retreived from a simulated environment, but cant be collected from a physical one making this important
    • The LSTM allows us to remember past information, thus allowing us to remember where cubes are and where other robots are
    • The CNN allows us to get numeric data from image inputs, thus allowing us to input each frame captured by the camera to the LSTM
  3. We train a control model based on SimBa1 using PPO (Proximal Policy Optimization)
    • This uses a custom environment and reward function

TO DO:

Footnotes

  1. SimBa

About

camera-based RL with state-reconstruction and object permanence

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages