Multiagent cooperation and competition with deep reinforcement learning

PLoS ONE

Volumn 12, Issue 4, 2017, Pages

  Tampuu, Ardi ^a   Matiisen, Tambet ^a   Kodelja, Dorian ^a,c   Kuzovkin, Ilya ^a   Korjus, Kristjan ^a   Aru, Juhan ^b   Aru, Jaan ^a   Vicente, Raul ^a  

^a UNIVERSITY OF TARTU   (Estonia)

^b ETH ZURICH   (Switzerland)

^c DIF   (France)

Author keywords

[No Author keywords available]

Indexed keywords

BEHAVIOR; COMPETITION; HUMAN; REINFORCEMENT; VIDEO GAME; ALGORITHM; COOPERATION; GAME; HUMAN RELATION; LEARNING; PHYSIOLOGY; REWARD; SOCIAL BEHAVIOR;

ALGORITHMS; COOPERATIVE BEHAVIOR; GAME THEORY; HUMANS; INTERPERSONAL RELATIONS; LEARNING; REINFORCEMENT (PSYCHOLOGY); REWARD; SOCIAL BEHAVIOR;

EID: 85017018413     PISSN: None     EISSN: 19326203     Source Type: Journal    
DOI: 10.1371/journal.pone.0172395     Document Type: Article

References (30)

1. Sutton RS, Barto AG. Reinforcement learning: An introduction. MIT press Cambridge; 1998.
2. Poole DL, Mackworth AK. Artificial Intelligence: foundations of computational agents. Cambridge University Press; 2010.
3. Busoniu L, Babuska R, De Schutter B. A comprehensive survey of multiagent reinforcement learning. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on. 2008;38(2):156-172. https://doi.org/10.1109/TSMCC.2007.913919
4. Sumpter DJ. Collective animal behavior. Princeton University Press; 2010.
5. Schwartz HM. Multi-Agent Machine Learning: A Reinforcement Approach. John Wiley & Sons; 2014.
6. Wang L, Sun S, Xia C. Finite-time stability of multi-agent system in disturbed environment. Nonlinear Dynamics. 2012;67(3):2009-2016. https://doi.org/10.1007/s11071-011-0125-0
7. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529-533. https://doi.org/10.1038/nature14236 PMID: 25719670
8. Koutnik J, Cuccu G, Schmidhuber J, Gomez F. Evolving large-scale neural networks for vision-based reinforcement learning. In: Proceedings of the 15th annual conference on Genetic and evolutionary computation. ACM; 2013. p. 1061-1068.
9. Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, et al. Playing atari with deep reinforcement learning. arXiv preprint arXiv:13125602. 2013;.
10. Lin LJ. Reinforcement learning for robots using neural networks. DTIC Document; 1993.
11. Schaul T, Quan J, Antonoglou I, Silver D. Prioritized Experience Replay. arXiv preprint arXiv:151105952. 2015;.
12. Tan M. Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the tenth international conference on machine learning; 1993. p. 330-337.
13. Claus C, Boutilier C. The dynamics of reinforcement learning in cooperative multiagent systems. In: AAAI/IAAI; 1998. p. 746-752.
14. Watkins CJCH. Learning from delayed rewards. University of Cambridge England; 1989.
15. Watkins CJ, Dayan P. Q-learning. Machine learning. 1992;8(3-4):279-292. https://doi.org/10.1023/A:1022676722315
16. Mott B, Anthony S. Stella: a multiplatform Atari 2600 VCS emulator; 2003.
17. Tesauro G. Temporal difference learning and TD-Gammon. Communications of the ACM. 1995;38(3):58-68. https://doi.org/10.1145/203330.203343
18. van der Ree M, Wiering M. Reinforcement learning in the game of Othello: learning against a fixed opponent and learning from self-play. In: Adaptive Dynamic Programming And Reinforcement Learning (ADPRL), 2013 IEEE Symposium on. IEEE; 2013. p. 108-115.
19. Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, et al. Mastering the game of Go with deep neural networks and tree search. Nature. 2016;529(7587):484-489. https://doi.org/10. 1038/nature16961 PMID: 26819042
20. Hasselt HV. Double Q-learning. In: Advances in Neural Information Processing Systems; 2010. p. 2613-2621.
21. Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M. Striving for simplicity: The all convolutional net. arXiv preprint arXiv:14126806. 2014;.
22. Yamins DL, DiCarlo JJ. Using goal-driven deep learning models to understand sensory cortex. Nature neuroscience. 2016;19(3):356-365. https://doi.org/10.1038/nn. 4244 PMID: 26906502
23. Guçlu U, van Gerven MA. Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. The Journal of Neuroscience. 2015;35(27):10005-10014. https://doi.org/10.1523/JNEUROSCI.5023-14.2015 PMID: 26157000
24. Mnih V, Heess N, Graves A, et al. Recurrent models of visual attention. In: Advances in Neural Information Processing Systems; 2014. p. 2204-2212.
25. Sukhbaatar S, Weston J, Fergus R, et al. End-to-end memory networks. In: Advances in Neural Information Processing Systems; 2015. p. 2431-2439.
26. Schmidhuber J. On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models. arXiv preprint arXiv:151109249. 2015;.
27. Foerster JN, Assael YM, de Freitas N, Whiteson S. Learning to communicate to solve riddles with deep distributed recurrent q-networks. arXiv preprint arXiv:160202672. 2016;.
28. Skyrms B. Signals: Evolution, learning, and information. OUP Oxford; 2010.
29. Binmore K. Do conventions need to be common knowledge? Topoi. 2008;27(1-2):17-27. https://doi.org/10.1007/s11245-008-9033-4
30. Lewis D. Convention: A philosophical study. John Wiley & Sons; 2008.