An environment model in multi-agent reinforcement learning with decentralized training

• Autorzy: Niedziółka-Domański Rafał , Bylina Jarosław

Identyfikatory

DOI

10.15439/2024F1840

• Konferencja: Federated Conference on Computer Science and Information Systems (19 ; 08-11.09.2024 ; Belgrade, Serbia)
• Języki publikacji: EN

Abstrakty

EN

In multi-agent reinforcement learning scenarios, independent learning, where agents learn independently based on their observations, is often preferred for its scalability and simplicity compared to centralized training. However, it faces significant challenges due to the non-stationary nature of the environment from each agent's perspective.

Słowa kluczowe

EN

reinforcement learning; multi-agent reinforcement; learning; model-based RL

PL

uczenie się przez wzmacnianie; system wieloagentowy; uczenie się; uczenie posiłkowane

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2024
• Tom: Vol. 39
• Strony: 661--666
• Opis fizyczny: Bibliogr. 14 poz., rys., wykr., wz.

Twórcy

autor

Niedziółka-Domański Rafał

• Maria Curie-Sklodowska University in Lublin, 5 M. Curie-Skłodowskiej Square, 20-031 Lublin, Poland

• https://orcid.org/0009-0004-0405-5508

autor

Bylina Jarosław

• Maria Curie-Sklodowska University in Lublin, 5 M. Curie-Skłodowskiej Square, 20-031 Lublin, Poland

• https://orcid.org/0000-0002-0319-2525

Bibliografia

• 1. S. V. Albrecht, F. Christianos, and L. Schäfer, Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press, 2024. [Online]. Available: https://www.marl-book.com
• 2. L. S. Shapley, “Stochastic games*,” Proceedings of the National Academy of Sciences, vol. 39, no. 10, pp. 1095–1100, 1953. http://dx.doi.org/10.1073/pnas.39.10.1095. [Online]. Available: https://www.pnas.org/doi/abs/10.1073/pnas.39.10.1095
• 3. R. Lowe, Y. Wu, A. Tamar, J. Harb, P. Abbeel, and I. Mordatch, “Multi-agent actor-critic for mixed cooperative-competitive environments,” CoRR, vol. abs/1706.02275, 2017. http://dx.doi.org/10.48550/arXiv.1706.02275. [Online]. Available: http://arxiv.org/abs/1706.02275
• 4. R. S. Sutton and A. G. Barto, Reinforcement Learning, 2nd ed., ser. Adaptive Computation and Machine Learning. Cambridge, MA: MIT Press, 2018. ISBN 978-0-262-03924-6. [Online]. Available: http://incompleteideas.net/book/the-book.html
• 5. T. M. Moerland, J. Broekens, A. Plaat, and C. M. Jonker, “Model-based reinforcement learning: A survey,” 2022. http://dx.doi.org/10.48550/arXiv.2006.16712
• 6. R. S. Sutton, “Integrated architectures for learning, planning, and reacting based on approximating dynamic programming,” in Machine Learning Proceedings 1990, B. Porter and R. Mooney, Eds. San Francisco (CA): Morgan Kaufmann, 1990, pp. 216–224. ISBN 978-1-55860-141-3. [Online]. Available: https://www.sciencedirect.com/science/article/pii/B9781558601413500304
• 7. D. Silver, T. Hubert, J. Schrittwieser, I. Antonoglou, M. Lai, A. Guez, M. Lanctot, L. Sifre, D. Kumaran, T. Graepel, T. P. Lillicrap, K. Simonyan, and D. Hassabis, “Mastering chess and shogi by self-play with a general reinforcement learning algorithm,” CoRR, vol. abs/1712.01815, 2017. http://dx.doi.org/10.48550/arXiv.1712.01815. [Online]. Available: http://arxiv.org/abs/1712.01815
• 8. M. Watter, J. T. Springenberg, J. Boedecker, and M. A. Riedmiller, “Embed to control: A locally linear latent dynamics model for control from raw images,” CoRR, vol. abs/1506.07365, 2015. [Online]. Available: http://arxiv.org/abs/1506.07365
• 9. R. S. Sutton, “Dyna, an integrated architecture for learning, planning, and reacting,” SIGART Bull., vol. 2, no. 4, p. 160–163, jul 1991. http://dx.doi.org/10.1145/122344.122377. [Online]. Available: https://doi.org/10.1145/122344.122377
• 10. W. Zhang, X. Wang, J. Shen, and M. Zhou, “Model-based multi-agent policy optimization with adaptive opponent-wise rollouts,” 2022. http://dx.doi.org/10.48550/arXiv.2105.03363
• 11. G. Tesauro, “Programming backgammon using self-teaching neural nets,” Artificial Intelligence, vol. 134, no. 1, pp. 181–199, 2002. http://dx.doi.org/10.1016/S0004-3702(01)00110-2. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0004370201001102
• 12. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” 2019. http://dx.doi.org/10.48550/arXiv.1711.05101
• 13. J. K. Terry, B. Black, N. Grammel, M. Jayakumar, A. Hari, R. Sullivan, L. Santos, R. Perez, C. Horsch, C. Dieffendahl, N. L. Williams, Y. Lokesh, and P. Ravi, “Pettingzoo: Gym for multi-agent reinforcement learning,” 2021.
• 14. V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning,” 2013. http://dx.doi.org/10.48550/arXiv.1312.5602

Uwagi

Thematic Sessions: Short Papers