Cited By
View all- Erus GPolat F(2018)A layered approach to learning coordination knowledge in multiagent environmentsApplied Intelligence10.1007/s10489-006-0034-y27:3(249-267)Online publication date: 28-Dec-2018
Learning intelligent behavior in a non-stationary and partially observable environment
Pages 97 - 115
Abstract
Individual learning in an environment where more than one agent exist is a challenging task. In this paper, a single learning agent situated in an environment where multiple agents exist is modeled based on reinforcement learning. The environment is non-stationary and partially accessible from an agents' point of view. Therefore, learning activities of an agent is influenced by actions of other cooperative or competitive agents in the environment. A prey-hunter capture game that has the above characteristics is defined and experimented to simulate the learning process of individual agents. Experimental results show that there are no strict rules for reinforcement learning. We suggest two new methods to improve the performance of agents. These methods decrease the number of states while keeping as much state as necessary.
References
[1]
Abul, O., Polat, F. & Alhajj, R. (2000). Multi-Agent Reinforcement Learning Using Function Approximation. IEEE Transaction on Systems, Man and Cybernetics30(4): 485-497.
[2]
Bellmann, R. E. (1957). Dynamic Programming. Princeton, NJ: Princeton University Press.
[3]
Ellis, H. C. (1972). Fundamentals of Human Learning and Cognition. Dubuque, Iowa: WM. C. Brown company Publishers.
[4]
Estes, W. K. (1970). Learning Theory and Mental Development. New York, NY: Academic Press.
[5]
Howard, R. A. (1960). Dynamic Programming and Markov Processes. Cambridge, MA: The MIT Press.
[6]
Hu, J. & Wellman, M. P. (1998). Multi-Agent Reinforcement Learning: Theoretical Framework and an Algorithm. Proc. of Int. Conf. on Machine Learning, 242-250.
[7]
Hu, J. & Wellman, M. P. (1998). Multiagent Reinforcement Learning and Stochastic Games. Games and Economic Behavior.
[8]
Hulse, S. H., Egeth, H. & Deese, J. (1984). The Psychology of Learning. McGraw-Hill
[9]
Kaelbling, L. P., Littman, M. L. & Moore, A: W. (1996). Reinfocement Learning: A Survey. Journal of Artificial Intelligence Research4: 237-285.
[10]
Kaelbling, L. P. et al. (1998). Planning and Acting in Partially Observable Stochastic Domains. Artificial Intelligence101.
[11]
Keller, F. S. (1969). Reinforcement Theory. New York, NY: Random House.
[12]
Kodratoff, Y. (1998). Introduction to Machine Learning. Morgan Kaufmann.
[13]
Kuter, U. & Polat, F. (2000). Learning Better in Dynamic, Partially Observable Environment. In Lindemann, G. (ed.) Proc. of European Conf. on Artificial Intelligence (ECAI) Workshop on Modeling Artificial Societies and Hybrid Organization, 50-68. Berlin, Aug. 20-25.
[14]
Langley, P. (1995). Elements of Machine Learning. Morgan Kaufman
[15]
Littman, M. L., Cassandra, A. R. & Kaelbling, L. P. (1995). Learning Policies for Partially Observable Environments: Scaling up. In Huhns, M. N. & Singh, M. P. (eds.) Readings in Agents, 495-503. Morgan Kaufman.
[16]
Minsky, M. (1961). Steps towards Artificial Intelligence. Proceedings of IRE, 8-30. Reprinted in Feigenbaum, E. A. & Feldman, J. (eds.) Computers and Thought, 406-450. New York, NY: McGraw-Hill.
[17]
Mitchell, T. M. (1997). Machine Learning. New York, NY: McGraw-Hill.
[18]
Polat, F, Guvenir, S. & Shekhar, S. (1993). A Negotiation Platform for Cooperating Multi-Agent Systems. International Journal of Concurrent Engineering:Research & Applications 3: 179-187.
[19]
Polat, F. & Guvenir, A. (1994). A Conflict Resolution Based Decentralized Multi-Agent Problem Solving Model. Artificial Social Systems, LNAI 130, 279-294. Springer-Verlag.
[20]
Russel, S. J. & Norvig, P. (1997). Artificial Intelligence: A Modern Approach. Englewood Cliffs, NJ: Prentice-Hall International, Inc.
[21]
Sen, S., Sekaran, M. & Hale, J. (1994). Learning to Coordinate without Sharing Information. In Huhns, M. N. & Singh, M. P. (eds.)Readings in Agents, 509-514. Morgan Kaufman.
[22]
Sutton, R. S. & Barto, A. G. (1998). Reinforcement Learning: An Introduction. MIT Press.
[23]
Tan, M. (1993). Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents. In Huhns, M. N. & Singh, M. P. (eds.) Readings in Agents, 487-494. Morgan Kaufman.
[24]
Turing, A. M. (1950). Computing Machinery and Intelligence. Mind95: 433-460. Reprinted in Mind design II, 29-56. Cambridge, MA: MIT Press.
[25]
Watkins, C. J. C. H. (1989). Learning from Delayed Rewards. PhD Thesis, University of Cambridge, England.
[26]
Watkins, C. J. C. H. & Dayan, P. (1992). Technical Note: Q-Learning. Machine Learning8: 279-292.
[27]
Weiß, G. (1996). Adaptation and Learning in Multi-Agent Systems: Some Remarks and a Bibliography. In Weiss, G. and Sen, S. (eds.) Adaption and Learning in Multi-Agent Systems. Berlin: Springer.
[28]
Weiss, G. (1999). Multi-Agent Systems: A Modern Approach to Distributed Artificial Intelligence, 28-77. Mit Press.
Index Terms
- Learning intelligent behavior in a non-stationary and partially observable environment
Recommendations
Learning sequences of actions in collectives of autonomous agents
AAMAS '02: Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. Directly applying ...
Evaluation of reinforcement learning techniques
IITM '10: Proceedings of the First International Conference on Intelligent Interactive Technologies and MultimediaReinforcement learning is became one of the most important approaches to machine intelligence. Now RL is widely use by different research field as intelligent control, robotics and neuroscience. It provides us possible solution within unknown ...
Introspective Reinforcement Learning and Learning from Demonstration
AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent SystemsReinforcement learning is a paradigm to model how an autonomous agent learns to maximise its cumulative reward by interacting with the environment. One challenge faced by reinforcement learning is that in many environments the reward signal is sparse, ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 01 October 2002
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
Cited By
View all- Erus GPolat F(2018)A layered approach to learning coordination knowledge in multiagent environmentsApplied Intelligence10.1007/s10489-006-0034-y27:3(249-267)Online publication date: 28-Dec-2018
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in