-
Notifications
You must be signed in to change notification settings - Fork 12
/
Copy pathbib-lecture.bib
1621 lines (1462 loc) · 52.4 KB
/
bib-lecture.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@incollection{scarf1959optimality,
title={The Optimality of (s, {S}) Policies in the Dynamic Inventory Problem},
author={Scarf, Herbert},
booktitle={Mathematical Methods in the Social Sciences},
editor={Arrow, Kenneth J. and Karlin, Samuel and Suppes, Patrick},
year={1959},
publisher={Stanford University Press},
address={Stanford, CA},
pages={196--202},
chapter={13}
}
@article{chen2021decision,
title={Decision transformer: Reinforcement learning via sequence modeling},
author={Chen, Lili and Lu, Kevin and Rajeswaran, Aravind and Lee, Kimin and Grover, Aditya and Laskin, Misha and Abbeel, Pieter and Srinivas, Aravind and Mordatch, Igor},
journal={Advances in neural information processing systems},
volume={34},
pages={15084--15097},
year={2021}
}
@book{altman2021constrained,
title={Constrained Markov decision processes},
author={Altman, Eitan},
year={2021},
publisher={Routledge}
}
@inproceedings{ng2000algorithms,
title={Algorithms for inverse reinforcement learning.},
author={Ng, Andrew Y and Russell, Stuart and others},
booktitle={Icml},
volume={1},
number={2},
pages={2},
year={2000}
}
@book{khalil1996robust,
title={Robust and optimal control},
author={Khalil, IS and Doyle, JC and Glover, K},
volume={2},
year={1996},
publisher={Prentice hall}
}
@article{mannor2013algorithmic,
title={Algorithmic aspects of mean--variance optimization in Markov decision processes},
author={Mannor, Shie and Tsitsiklis, John N},
journal={European Journal of Operational Research},
volume={231},
number={3},
pages={645--653},
year={2013},
publisher={Elsevier}
}
@article{mannor2004geometric,
title={A geometric approach to multi-criterion reinforcement learning},
author={Mannor, Shie and Shimkin, Nahum},
journal={The Journal of Machine Learning Research},
volume={5},
pages={325--360},
year={2004},
publisher={JMLR. org}
}
@article{kaufmann2023champion,
title={Champion-level drone racing using deep reinforcement learning},
author={Kaufmann, Elia and Bauersfeld, Leonard and Loquercio, Antonio and M{\"u}ller, Matthias and Koltun, Vladlen and Scaramuzza, Davide},
journal={Nature},
volume={620},
number={7976},
pages={982--987},
year={2023},
publisher={Nature Publishing Group UK London}
}
@article{vinyals2019grandmaster,
title={Grandmaster level in StarCraft II using multi-agent reinforcement learning},
author={Vinyals, Oriol and Babuschkin, Igor and Czarnecki, Wojciech M and Mathieu, Micha{\"e}l and Dudzik, Andrew and Chung, Junyoung and Choi, David H and Powell, Richard and Ewalds, Timo and Georgiev, Petko and others},
journal={nature},
volume={575},
number={7782},
pages={350--354},
year={2019},
publisher={Nature Publishing Group}
}
@book{russell2016artificial,
title={Artificial intelligence: a modern approach},
author={Russell, Stuart J and Norvig, Peter},
year={2016},
publisher={Pearson}
}
@book{powell2007approximate,
title={Approximate Dynamic Programming: Solving the curses of dimensionality},
author={Powell, Warren B},
volume={703},
year={2007},
publisher={John Wiley \& Sons}
}
@article{bemporad1999control,
title={Control of systems integrating logic, dynamics, and constraints},
author={Bemporad, Alberto and Morari, Manfred},
journal={Automatica},
volume={35},
number={3},
pages={407--427},
year={1999},
publisher={Elsevier}
}
@book{kirk2004optimal,
title={Optimal control theory: an introduction},
author={Kirk, Donald E},
year={2004},
publisher={Courier Corporation}
}
@inproceedings{zhang2023planning,
title={Planning with Large Language Models for Code Generation},
author={Zhang, Shun and Chen, Zhenfang and Shen, Yikang and Ding, Mingyu and Tenenbaum, Joshua B. and Gan, Chuang},
booktitle={Proceedings of the International Conference on Learning Representations (ICLR)},
year={2023},
}
@article{ouyang2022training,
title={Training language models to follow instructions with human feedback},
author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},
journal={Advances in neural information processing systems},
volume={35},
pages={27730--27744},
year={2022}
}
@article{levine2016end,
title={End-to-end training of deep visuomotor policies},
author={Levine, Sergey and Finn, Chelsea and Darrell, Trevor and Abbeel, Pieter},
journal={Journal of Machine Learning Research},
volume={17},
number={39},
pages={1--40},
year={2016}
}
@article{taylor2009transfer,
title={Transfer learning for reinforcement learning domains: A survey.},
author={Taylor, Matthew E and Stone, Peter},
journal={Journal of Machine Learning Research},
volume={10},
number={7},
year={2009}
}
@article{khetarpal2022towards,
title={Towards continual reinforcement learning: A review and perspectives},
author={Khetarpal, Khimya and Riemer, Matthew and Rish, Irina and Precup, Doina},
journal={Journal of Artificial Intelligence Research},
volume={75},
pages={1401--1476},
year={2022}
}
@article{nilim2005robust,
title={Robust control of Markov decision processes with uncertain transition matrices},
author={Nilim, Arnab and El Ghaoui, Laurent},
journal={Operations Research},
volume={53},
number={5},
pages={780--798},
year={2005},
publisher={INFORMS}
}
@inproceedings{tobin2017domain,
title={Domain randomization for transferring deep neural networks from simulation to the real world},
author={Tobin, Josh and Fong, Rachel and Ray, Alex and Schneider, Jonas and Zaremba, Wojciech and Abbeel, Pieter},
booktitle={2017 IEEE/RSJ international conference on intelligent robots and systems (IROS)},
pages={23--30},
year={2017},
organization={IEEE}
}
@article{kirk2023survey,
title={A survey of zero-shot generalisation in deep reinforcement learning},
author={Kirk, Robert and Zhang, Amy and Grefenstette, Edward and Rockt{\"a}schel, Tim},
journal={Journal of Artificial Intelligence Research},
volume={76},
pages={201--264},
year={2023}
}
@article{ghavamzadeh2015bayesian,
title={Bayesian reinforcement learning: A survey},
author={Ghavamzadeh, Mohammad and Mannor, Shie and Pineau, Joelle and Tamar, Aviv and others},
journal={Foundations and Trends{\textregistered} in Machine Learning},
volume={8},
number={5-6},
pages={359--483},
year={2015},
publisher={Now Publishers, Inc.}
}
@article{beck2023survey,
title={A survey of meta-reinforcement learning},
author={Beck, Jacob and Vuorio, Risto and Liu, Evan Zheran and Xiong, Zheng and Zintgraf, Luisa and Finn, Chelsea and Whiteson, Shimon},
journal={arXiv preprint arXiv:2301.08028},
year={2023}
}
@article{hallak2015contextual,
title={Contextual markov decision processes},
author={Hallak, Assaf and Di Castro, Dotan and Mannor, Shie},
journal={arXiv preprint arXiv:1502.02259},
year={2015}
}
@inproceedings{tamar2022regularization,
title={Regularization guarantees generalization in bayesian reinforcement learning through algorithmic stability},
author={Tamar, Aviv and Soudry, Daniel and Zisselman, Ev},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={36},
number={8},
pages={8423--8431},
year={2022}
}
@article{srivastava2019training,
title={Training agents using upside-down reinforcement learning},
author={Srivastava, Rupesh Kumar and Shyam, Pranav and Mutz, Filipe and Ja{\'s}kowski, Wojciech and Schmidhuber, J{\"u}rgen},
journal={arXiv preprint arXiv:1912.02877},
year={2019}
}
@inproceedings{kaelbling1993learning,
title={Learning to achieve goals},
author={Kaelbling, Leslie Pack},
booktitle={IJCAI},
volume={2},
pages={1094--8},
year={1993},
organization={Citeseer}
}
@article{lake2017building,
title={Building machines that learn and think like people},
author={Lake, Brenden M and Ullman, Tomer D and Tenenbaum, Joshua B and Gershman, Samuel J},
journal={Behavioral and brain sciences},
volume={40},
pages={e253},
year={2017},
publisher={Cambridge University Press}
}
@book{astrom2008adaptive,
title={Adaptive Control},
author={{\AA}str{\"o}m, K.J. and Wittenmark, B.},
isbn={9780486462783},
lccn={2008007690},
series={Dover Books on Electrical Engineering},
url={https://books.google.co.il/books?id=L0m_CR-IK24C},
year={2008},
publisher={Dover Publications}
}
@article{sutton1992reinforcement,
title={Reinforcement learning is direct adaptive optimal control},
author={Sutton, Richard S and Barto, Andrew G and Williams, Ronald J},
journal={IEEE control systems magazine},
volume={12},
number={2},
pages={19--22},
year={1992},
publisher={IEEE}
}
@article{dijkstra1959note,
title={A note on two problems in connexion with graphs},
author={Dijkstra, EW},
journal={Numerische Mathematik},
volume={1},
pages={269--271},
year={1959},
publisher={Springer}
}
@book{hirsch2013differential,
title={Differential equations, dynamical systems, and an introduction to chaos},
author={Hirsch, Morris W and Smale, Stephen and Devaney, Robert L},
year={2013},
publisher={Academic press}
}
@book{khalil2002nonlinear,
title={Nonlinear Systems},
author={Khalil, H.K.},
isbn={9780130673893},
lccn={95045804},
series={Pearson Education},
url={https://books.google.co.il/books?id=t_d1QgAACAAJ},
year={2002},
publisher={Prentice Hall}
}
@article{latif2014banach,
title={Banach contraction principle and its generalizations},
author={Latif, Abdul},
journal={Topics in fixed point theory},
pages={33--64},
year={2014},
publisher={Springer}
}
@book{JacobsonMayne1970,
title={Differential Dynamic Programming},
author={Jacobson, Donald E. and Mayne, David Q.},
year={1970},
publisher={American Elsevier Publishing Company},
address={New York}
}
@inproceedings{todorov2005generalized,
title={A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems},
author={Todorov, Emanuel and Li, Weiwei},
booktitle={Proceedings of the 2005, American Control Conference, 2005.},
pages={300--306},
year={2005},
organization={IEEE}
}
@article{viterbi1967error,
title={Error bounds for convolutional codes and an asymptotically optimum decoding algorithm},
author={Viterbi, Andrew},
journal={IEEE transactions on Information Theory},
volume={13},
number={2},
pages={260--269},
year={1967},
publisher={IEEE}
}
@article{hart1968formal,
title={A formal basis for the heuristic determination of minimum cost paths},
author={Hart, Peter E and Nilsson, Nils J and Raphael, Bertram},
journal={IEEE transactions on Systems Science and Cybernetics},
volume={4},
number={2},
pages={100--107},
year={1968},
publisher={IEEE}
}
@inproceedings{ng1999policy,
title={Policy invariance under reward transformations: Theory and application to reward shaping},
author={Ng, Andrew Y and Harada, Daishi and Russell, Stuart},
booktitle={International Conference on Machine Learning},
volume={99},
pages={278--287},
year={1999}
}
@article{greensmith2004variance,
title={Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.},
author={Greensmith, Evan and Bartlett, Peter L and Baxter, Jonathan},
journal={Journal of Machine Learning Research},
volume={5},
number={9},
year={2004}
}
@inproceedings{scherrer2014local,
title={Local policy search in a convex space and conservative policy iteration as boosted policy search},
author={Scherrer, Bruno and Geist, Matthieu},
booktitle={Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part III 14},
pages={35--50},
year={2014},
organization={Springer}
}
@article{schulman2017proximal,
title={Proximal policy optimization algorithms},
author={Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
journal={arXiv preprint arXiv:1707.06347},
year={2017}
}
@article{KearnsS02,
author = {Michael J. Kearns and
Satinder P. Singh},
title = {Near-Optimal Reinforcement Learning in Polynomial Time},
journal = {Machine Learning},
volume = {49},
number = {2-3},
pages = {209--232},
year = {2002},
url = {https://doi.org/10.1023/A:1017984413808},
doi = {10.1023/A:1017984413808},
timestamp = {Sun, 28 May 2017 13:18:23 +0200},
biburl = {https://dblp.org/rec/bib/journals/ml/KearnsS02},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{kushner2003stochastic,
title={{Stochastic approximation and recursive algorithms and applications}},
author={Kushner, H.J. and Yin, G.},
year={2003},
publisher={Springer Verlag}
}
@book{borkar2009stochastic,
title={Stochastic approximation: a dynamical systems viewpoint},
author={Borkar, Vivek S},
volume={48},
year={2009},
publisher={Springer}
}
@article{munos2007performance,
title={Performance bounds in l\_p-norm for approximate value iteration},
author={Munos, R{\'e}mi},
journal={SIAM journal on control and optimization},
volume={46},
number={2},
pages={541--561},
year={2007},
publisher={SIAM}
}
@inproceedings{kearns2000bias,
title={Bias-Variance Error Bounds for Temporal Difference Updates.},
author={Kearns, Michael J and Singh, Satinder},
booktitle={COLT},
pages={142--147},
year={2000}
}
@inproceedings{KearnsS98a,
author = {Michael J. Kearns and
Satinder P. Singh},
title = {Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms},
booktitle = {Advances in Neural Information Processing Systems 11, {[NIPS} Conference,
Denver, Colorado, USA, November 30 - December 5, 1998]},
pages = {996--1002},
year = {1998}
}
@article{BrafmanT02,
author = {Ronen I. Brafman and
Moshe Tennenholtz},
title = {{R-MAX} - {A} General Polynomial Time Algorithm for Near-Optimal Reinforcement
Learning},
journal = {Journal of Machine Learning Research},
volume = {3},
pages = {213--231},
year = {2002},
url = {http://www.jmlr.org/papers/v3/brafman02a.html},
timestamp = {Thu, 05 Feb 2004 13:43:02 +0100},
biburl = {https://dblp.org/rec/bib/journals/jmlr/BrafmanT02},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{StrehlLL09,
author = {Alexander L. Strehl and
Lihong Li and
Michael L. Littman},
title = {Reinforcement Learning in Finite MDPs: {PAC} Analysis},
journal = {Journal of Machine Learning Research},
volume = {10},
pages = {2413--2444},
year = {2009},
url = {http://doi.acm.org/10.1145/1577069.1755867},
doi = {10.1145/1577069.1755867},
timestamp = {Mon, 13 Nov 2017 02:31:07 +0100},
biburl = {https://dblp.org/rec/bib/journals/jmlr/StrehlLL09},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@Inbook{Li2012,
author="Li, Lihong",
title="Sample Complexity Bounds of Exploration",
bookTitle="Reinforcement Learning: State-of-the-Art",
year="2012",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="175--204",
abstract="Efficient exploration is widely recognized as a fundamental challenge inherent in reinforcement learning. Algorithms that explore efficiently converge faster to near-optimal policies. While heuristics techniques are popular in practice, they lack formal guarantees and may not work well in general. This chapter studies algorithms with polynomial sample complexity of exploration, both model-based and model-free ones, in a unified manner. These so-called PAC-MDP algorithms behave near-optimally except in a ``small'' number of steps with high probability. A new learning model known as KWIK is used to unify most existing model-based PAC-MDP algorithms for various subclasses of Markov decision processes.We also compare the sample-complexity framework to alternatives for formalizing exploration efficiency such as regret minimization and Bayes optimal solutions.",
isbn="978-3-642-27645-3",
doi="10.1007/978-3-642-27645-3_6",
url="https://doi.org/10.1007/978-3-642-27645-3_6"
}
@article{SinghS96,
author = {Satinder P. Singh and
Richard S. Sutton},
title = {Reinforcement Learning with Replacing Eligibility Traces},
journal = {Machine Learning},
volume = {22},
number = {1-3},
pages = {123--158},
year = {1996},
url = {https://doi.org/10.1023/A:1018012322525},
doi = {10.1023/A:1018012322525},
timestamp = {Sun, 28 May 2017 13:18:24 +0200},
biburl = {https://dblp.org/rec/bib/journals/ml/SinghS96},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Even-DarM03,
author = {Eyal Even{-}Dar and
Yishay Mansour},
title = {Learning Rates for Q-learning},
journal = {Journal of Machine Learning Research},
volume = {5},
pages = {1--25},
year = {2003},
url = {http://www.jmlr.org/papers/v5/evendar03a.html},
timestamp = {Thu, 05 Feb 2004 13:53:36 +0100},
biburl = {https://dblp.org/rec/bib/journals/jmlr/Even-DarM03},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{SeijenHWW09,
author = {Harm van Seijen and
Hado van Hasselt and
Shimon Whiteson and
Marco A. Wiering},
title = {A theoretical and empirical analysis of Expected Sarsa},
booktitle = {{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement
Learning, {ADPRL} 2009, Nashville, TN, USA, March 31 - April 1, 2009},
pages = {177--184},
year = {2009}
}
@book{SuttonB98,
author = {Richard S. Sutton and
Andrew G. Barto},
title = {Reinforcement learning - an introduction},
series = {Adaptive computation and machine learning},
publisher = {{MIT} Press},
year = {1998},
url = {http://www.worldcat.org/oclc/37293240},
isbn = {0262193981},
timestamp = {Wed, 26 Apr 2017 17:48:08 +0200},
biburl = {https://dblp.org/rec/bib/books/lib/SuttonB98},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Tesauro95,
author = {Gerald Tesauro},
title = {Temporal Difference Learning and TD-Gammon},
journal = {Commun. {ACM}},
volume = {38},
number = {3},
pages = {58--68},
year = {1995},
url = {http://doi.acm.org/10.1145/203330.203343},
doi = {10.1145/203330.203343},
timestamp = {Tue, 07 Jun 2011 16:52:36 +0200},
biburl = {https://dblp.org/rec/bib/journals/cacm/Tesauro95},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Tesauro02,
author = {Gerald Tesauro},
title = {Programming backgammon using self-teaching neural nets},
journal = {Artif. Intell.},
volume = {134},
number = {1-2},
pages = {181--199},
year = {2002},
url = {https://doi.org/10.1016/S0004-3702(01)00110-2},
doi = {10.1016/S0004-3702(01)00110-2},
timestamp = {Sat, 27 May 2017 14:24:43 +0200},
biburl = {https://dblp.org/rec/bib/journals/ai/Tesauro02},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{MnihKSRVBGRFOPB15,
author = {Volodymyr Mnih and
Koray Kavukcuoglu and
David Silver and
Andrei A. Rusu and
Joel Veness and
Marc G. Bellemare and
Alex Graves and
Martin A. Riedmiller and
Andreas Fidjeland and
Georg Ostrovski and
Stig Petersen and
Charles Beattie and
Amir Sadik and
Ioannis Antonoglou and
Helen King and
Dharshan Kumaran and
Daan Wierstra and
Shane Legg and
Demis Hassabis},
title = {Human-level control through deep reinforcement learning},
journal = {Nature},
volume = {518},
number = {7540},
pages = {529--533},
year = {2015},
url = {https://doi.org/10.1038/nature14236},
doi = {10.1038/nature14236},
timestamp = {Sat, 20 May 2017 00:24:51 +0200},
biburl = {https://dblp.org/rec/bib/journals/nature/MnihKSRVBGRFOPB15},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{KohlS04,
author = {Nate Kohl and
Peter Stone},
title = {Policy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion},
booktitle = {Proceedings of the 2004 {IEEE} International Conference on Robotics
and Automation, {ICRA} 2004, April 26 - May 1, 2004, New Orleans,
LA, {USA}},
pages = {2619--2624},
year = {2004}
}
@article{SilverHMGSDSAPL16,
author = {David Silver and
Aja Huang and
Chris J. Maddison and
Arthur Guez and
Laurent Sifre and
George van den Driessche and
Julian Schrittwieser and
Ioannis Antonoglou and
Vedavyas Panneershelvam and
Marc Lanctot and
Sander Dieleman and
Dominik Grewe and
John Nham and
Nal Kalchbrenner and
Ilya Sutskever and
Timothy P. Lillicrap and
Madeleine Leach and
Koray Kavukcuoglu and
Thore Graepel and
Demis Hassabis},
title = {Mastering the game of {Go} with deep neural networks and tree search},
journal = {Nature},
volume = {529},
number = {7587},
pages = {484--489},
year = {2016},
url = {https://doi.org/10.1038/nature16961},
doi = {10.1038/nature16961},
timestamp = {Sat, 20 May 2017 00:24:51 +0200},
biburl = {https://dblp.org/rec/bib/journals/nature/SilverHMGSDSAPL16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{AbbeelCN2010,
author = {Abbeel, Pieter and Coates, Adam and Ng, Andrew Y.},
title = {Autonomous Helicopter Aerobatics Through Apprenticeship Learning},
journal = {Int. J. Rob. Res.},
issue_date = {November 2010},
volume = {29},
number = {13},
month = nov,
year = {2010},
issn = {0278-3649},
pages = {1608--1639},
numpages = {32},
url = {http://dx.doi.org/10.1177/0278364910371999},
doi = {10.1177/0278364910371999},
acmid = {1894944},
publisher = {Sage Publications, Inc.},
address = {Thousand Oaks, CA, USA},
keywords = {Apprenticeship learning, autonomous flight, autonomous helicopter, helicopter aerobatics, learning from demonstrations},
}
@inproceedings{KearnsMN99,
author = {Michael J. Kearns and
Yishay Mansour and
Andrew Y. Ng},
title = {Approximate Planning in Large POMDPs via Reusable Trajectories},
booktitle = {Advances in Neural Information Processing Systems 12, {[NIPS} Conference,
Denver, Colorado, USA, November 29 - December 4, 1999]},
pages = {1001--1007},
year = {1999},
crossref = {DBLP:conf/nips/1999},
url = {http://papers.nips.cc/paper/1664-approximate-planning-in-large-pomdps-via-reusable-trajectories},
timestamp = {Thu, 11 Dec 2014 17:34:08 +0100},
biburl = {https://dblp.org/rec/bib/conf/nips/KearnsMN99},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{KearnsMN02,
author = {Michael J. Kearns and
Yishay Mansour and
Andrew Y. Ng},
title = {A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov
Decision Processes},
journal = {Machine Learning},
volume = {49},
number = {2-3},
pages = {193--208},
year = {2002},
url = {https://doi.org/10.1023/A:1017932429737},
doi = {10.1023/A:1017932429737},
timestamp = {Sun, 28 May 2017 13:18:23 +0200},
biburl = {https://dblp.org/rec/bib/journals/ml/KearnsMN02},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{PieterN04,
author = {Pieter Abbeel and
Andrew Y. Ng},
title = {Apprenticeship learning via inverse reinforcement learning},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
year = {2004}
}
@inproceedings{NgR00,
author = {Andrew Y. Ng and
Stuart J. Russell},
title = {Algorithms for Inverse Reinforcement Learning},
booktitle = {Proceedings of the Seventeenth International Conference on Machine
Learning {(ICML} 2000), Stanford University, Stanford, CA, USA, June
29 - July 2, 2000},
pages = {663--670},
year = {2000}
}
@article{TsitsiklisVR97,
author = {J. Tsitsiklis and B. Van Roy},
title = {An Analysis of Temporal-Difference Learning with Function Approximation},
journal = {IEEE Trans. on Automatic Control},
volume = {42},
number = {5},
year = {1997},
pages = {674--690},
}
@book{BookCormenLRS2009,
author = {Thomas H. Cormen and
Charles E. Leiserson and
Ronald L. Rivest and
Clifford Stein},
title = {Introduction to Algorithms, 3rd Edition},
publisher = {{MIT} Press},
year = {2009},
url = {http://mitpress.mit.edu/books/introduction-algorithms}
}
@article{kearns2002sparse,
title={A sparse sampling algorithm for near-optimal planning in large Markov decision processes},
author={Kearns, Michael and Mansour, Yishay and Ng, Andrew Y},
journal={Machine learning},
volume={49},
number={2-3},
pages={193--208},
year={2002},
publisher={Springer}
}
@inproceedings{kocsis2006bandit,
title={Bandit based monte-carlo planning},
author={Kocsis, Levente and Szepesv{\'a}ri, Csaba},
booktitle={European conference on machine learning},
pages={282--293},
year={2006},
organization={Springer}
}
@incollection{gordon1995stable,
title={Stable function approximation in dynamic programming},
author={Gordon, Geoffrey J},
booktitle={Machine Learning Proceedings 1995},
pages={261--268},
year={1995},
publisher={Elsevier}
}
@article{silver2016mastering,
title={Mastering the game of Go with deep neural networks and tree search},
author={Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
journal={Nature},
volume={529},
number={7587},
pages={484--489},
year={2016},
publisher={Nature Publishing Group}
}
@article{silver2017mastering,
title={Mastering the game of go without human knowledge},
author={Silver, David and Schrittwieser, Julian and Simonyan, Karen and Antonoglou, Ioannis and Huang, Aja and Guez, Arthur and Hubert, Thomas and Baker, Lucas and Lai, Matthew and Bolton, Adrian and others},
journal={Nature},
volume={550},
number={7676},
pages={354--359},
year={2017},
publisher={Nature Publishing Group}
}
@article{mnih2015human,
title={Human-level control through deep reinforcement learning},
author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
journal={nature},
volume={518},
number={7540},
pages={529--533},
year={2015},
publisher={Nature Publishing Group}
}
@article{Samuel62,
author = {Arthur L. Samuel},
title = {Artificial intelligence - a frontier of automation},
journal = {Elektron. Rechenanlagen},
volume = {4},
number = {4},
pages = {173--177},
year = {1962},
url = {https://doi.org/10.1524/itit.1962.4.16.173},
doi = {10.1524/itit.1962.4.16.173},
timestamp = {Mon, 18 May 2020 12:40:49 +0200},
biburl = {https://dblp.org/rec/journals/it/Samuel62.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DeepBlue,
title = {Deep Blue},
journal = {Artificial Intelligence},
volume = {134},
number = {1},
pages = {57-83},
year = {2002},
issn = {0004-3702},
doi = {https://doi.org/10.1016/S0004-3702(01)00129-1},
url = {https://www.sciencedirect.com/science/article/pii/S0004370201001291},
author = {Murray Campbell and A.Joseph Hoane and Feng-hsiung Hsu},
keywords = {Computer chess, Game tree search, Parallel search, Selective search, Search extensions, Evaluation function},
abstract = {Deep Blue is the chess machine that defeated then-reigning World Chess Champion Garry Kasparov in a six-game match in 1997. There were a number of factors that contributed to this success, including: •a single-chip chess search engine,•a massively parallel system with multiple levels of parallelism,•a strong emphasis on search extensions,•a complex evaluation function, and•effective use of a Grandmaster game database. This paper describes the Deep Blue system, and gives some of the rationale that went into the design decisions behind Deep Blue.}
}
@article{Karp78,
author = {Richard M. Karp},
title = {A characterization of the minimum cycle mean in a digraph},
journal = {Discret. Math.},
volume = {23},
number = {3},
pages = {309--311},
year = {1978},
url = {https://doi.org/10.1016/0012-365X(78)90011-0},
doi = {10.1016/0012-365X(78)90011-0},
timestamp = {Fri, 12 Feb 2021 13:44:46 +0100},
biburl = {https://dblp.org/rec/journals/dm/Karp78.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{ChaturvediM17,
author = {Mmanu Chaturvedi and
Ross M. McConnell},
title = {A note on finding minimum mean cycle},
journal = {Inf. Process. Lett.},
volume = {127},
pages = {21--22},
year = {2017},
url = {https://doi.org/10.1016/j.ipl.2017.06.007},
doi = {10.1016/j.ipl.2017.06.007},
timestamp = {Tue, 12 Sep 2017 17:58:15 +0200},
biburl = {https://dblp.org/rec/journals/ipl/ChaturvediM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{cormen2009introduction,
title={Introduction to algorithms},
author={Cormen, Thomas H and Leiserson, Charles E and Rivest, Ronald L and Stein, Clifford},
year={2009},
publisher={MIT press}
}
@book{KleinbergTardos06,
author = {Kleinberg, Jon and Tardos, \'Eva},
publisher = {Addison Wesley},
title = {Algorithm Design},
year = 2006
}
@book{DasguptaPapadimitriouVazirani08,
author = {Sanjoy Dasgupta and
Christos H. Papadimitriou and
Umesh V. Vazirani},
title = {Algorithms},
publisher = {McGraw-Hill},
year = {2008}
}
@book{van1996weak,
title={Weak Convergence and Empirical Processes: With Applications to Statistics},
author={van der Vaart, AW and van der Vaart, A.W. and van der Vaart, A. and Wellner, J.},
isbn={9780387946405},
lccn={95049099},
series={Springer Series in Statistics},
url={https://books.google.fr/books?id=seH8dMrEgggC},
year={1996},
publisher={Springer}
}
@book{Howard1960,
author = {Howard, R. A.},
publisher = {MIT Press},
title = {Dynamic Programming and Markov Processes},
year = 1960
}
@book{Bellman:DynamicProgramming,
author = {Bellman, Richard},
publisher = {Dover Publications},
title = {{Dynamic Programming}},
year = 1957
}
@article{Bellman54,
author = {Richard Bellman},
title = {The theory of dynamic programming},
journal = {Bull. Amer. Math. Soc.},
volume = {60},
number = {6},
pages = {503–515},
year = {1954},
note = {Defines value iteration?}
}
@article{Shapley53,
author = {L. S. Shapley},
title = {Stochastic games},
journal = {Proc Natl Acad Sci USA},
volume = {39},
pages = {1095–-1100},
year = {1953}
}
@Inbook{Zhang2021,
author="Zhang, Kaiqing
and Yang, Zhuoran
and Ba{\c{s}}ar, Tamer",
editor="Vamvoudakis, Kyriakos G.
and Wan, Yan
and Lewis, Frank L.
and Cansever, Derya",
title="Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms",
bookTitle="Handbook of Reinforcement Learning and Control",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="321--384"
}
@book{puterman2014markov,
author = {Puterman, Martin L},
publisher = {John Wiley \& Sons},
title = {Markov decision processes: discrete stochastic dynamic programming},
year = 2014
}
@book{BertsekasTsitsiklis96,
author = {Bertsekas, D. P. and Tsitsiklis, J. N.},
booktitle = {Neuro-dynamic programming.},
publisher = {Athena Scientific},
title = {Neuro-dynamic programming.},
year = 1996
}
@book{Bertsekas05,
author = {Dimitri P. Bertsekas},
title = {Dynamic programming and optimal control, 3rd Edition},
publisher = {Athena Scientific},
year = {2005}
}
@book{Szepesvari,
author = {Csaba Szepesv{\'{a}}ri},
title = {Algorithms for Reinforcement Learning},
series = {Synthesis Lectures on Artificial Intelligence and Machine Learning},
publisher = {Morgan {\&} Claypool Publishers},
year = {2010},
}
@comment{Papers for policy and value iteration discounted, chapter 5 discounted}
@inproceedings{LittmanDK95,
author = {Michael L. Littman and
Thomas L. Dean and
Leslie Pack Kaelbling},