Abstract
Reinforcement learning is one of the most popular learning method for machine learning. Some reinforcement learning algorithms for adapting to the dynamic environment are proposed. In this paper, the number of episode to suppress the ineffective rule after the change of the environment was examined analytically. Afterwards, the forgettable profit sharing method to suppress the ineffective rule quickly is proposed, and the effectiveness was experimentally confirmed comparing the proposed method with conventional method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Leslie Pack Kealbling, Michael L. Littman, and Andrew W. Moore: Reinforcement Learning: A Survey, Journal of Artificial Intelligence Research 4, pp237–285(1996)
Miyazaki, K., and Kobayashi, S.: Reinforcement Learning Systems for Discrete Markov Decision Processes, JJSAI,Vol.12,No.6,pp811–821(1997)
Miyazaki, K., Yamamura, M., and Kobayashi, S.: MarcoPolo: A Reinforcement Learning System Considering Tradeoff Exploitation and Exploration under Markovian Environments, JSSAI, Vol.12, No.1, pp78–88(1997)
Yamaguchi, T., Masubuchi, M., Fujihara, K., and Yachida, M.: Accelerating Reinforcement Learning for a Real Robot with Automated Abstract Sub-Rewards Generation, JSSAI, Vol.12, No.5, pp712–723(1997)
Minoru A.: Research Issues on Real Robot Reinforcement Learning, JSSAI, Vol.12, No.6, pp.831–836(1997)
Devika Subramanian, Peter Druschel, and Johnny Chen: Ants and reinforcement learning: A case study in routing in dynamic networks, In Proceedings of IJCAI-97, 1997.
Justin A. Boyan and Michael L. Littman. Packet routing in dynamically changing networks: A reinforcement learning approach. In Jack D. Cowan, Gerald Tesauro, and Joshua Alspector, editors, Advances in Neural Information Processing Systems, volume 6, pages 671–678. Morgan Kaufmann, San Francisco CA, 1993
Arai, S., Miyazaki, K., and Kobayashi, S.: Methodology in Multi-Agent Reinforcement Learning-Approaches by Q-learning and Profit Sharing-, JJSAI, Vol.13, No.4, pp609–617(1998)
Unemi, T.: Collective Behavior of Reinforcement Learning Agents, MACC, pp137–150(1993)
Yamamura, M., Miyazaki, K., and Kobayashi, S.: A Survey on Learning for Agents, JSSAI, Vol.10, No.5, pp683–689(1995)
Yamaguchi, T., Miura, M., and Yachida, M.: Multi-Agent Reinforcement Learning with Adaptive Mimetism, JSSAI, Vol.12, No.2, pp323–330(1997)
Miyazaki, K., Arai, S., and Kobayashi, S.: A Theory of Profit Sharing in Multi-Agent Reinforcement Learning, JSSAI, Vol.14, No.6, pp1156–1164(1999)
Kimura, H., Yamamura, M., and Kobayashi, S.: Reinforcement Learning in Partially Observable Markov Decision Processes: A Stochastic Gradient Method, JSSAI, Vol.11, No.5, pp761–768(1996)
Yamamoto, S., Yamaguchi, F., Saito, H., and Nakanishi, M.: A recognization method of environmental change on reinforcement learning, TECHNICAL REPORT OF Institute of Electronics Information and Communication Engineers, AI99-81, pp31–36(2000-01)
Miyazaki, K., Yamamura, M., and Kobayashi, S.: A Theory of Profit Sharing in Reinforcement Learning, JJSAI, Vol.9, No.4, pp.580–587(1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kato, S., Matsuo, H. (2000). A Theory of Profit Sharing in Dynamic Environment. In: Mizoguchi, R., Slaney, J. (eds) PRICAI 2000 Topics in Artificial Intelligence. PRICAI 2000. Lecture Notes in Computer Science(), vol 1886. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44533-1_15
Download citation
DOI: https://doi.org/10.1007/3-540-44533-1_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67925-7
Online ISBN: 978-3-540-44533-3
eBook Packages: Springer Book Archive