Abstract
Reinforcement learning agents are used in many domains; however, multiple, benevolent, and communicating reinforcement learning agents are rarely used. This paper explores using multiple reinforcement learning agents in a simple static environment to research methods allowing such agents to communicate during learning. The problem of developing a model whereby reinforcement learning agents can learn faster through the use of communication is explored. This paper develops two agents that are able to communicate with each other and able to learn about their actions using reinforcement learning techniques. The maze environment is used as a testbed. In this environment, the two agents are required to navigate the maze and trade information about the state of each other. This information includes the expected utilities for all actions from that state. To demonstrate the feasibility of the proposed approach, the agents are implemented. In addition, the efficiency of this model is compared with single agents and two independent agents.
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
Bigus, J.P., Bigus, J.: Constructing Intelligent Agents Using Java, 2nd edn. John Wiley and Sons, Inc., Chichester (2001)
Finin, T., Labrou, Y., Mayfield, J.: KQML as an Agent Communication Language. In: Bradshaw, J.M. (ed.) Software Agents, pp. 291–316. AAA/MIT Press, Cambridge, MA (1997)
Littman, M.L.: Markov Games as a Framework for Multi-agent Reinforcement Learning. In: The Proceedings of the 11th International Conference on Machine Learning (ML 1994), pp. 157–163. Morgan Kaufmann, New Brunswick (1994)
Makar, R., Magadevan, S., Ghavamzadeh, M.: Hierarchial Multi-Agent Reinforcement Learning. In: Proceedings of the Fith International Conference on Autonomus Agents, Montreal, Quebec, pp. 246–253. ACM Press, New York (2001)
Perez-Uribe, A.: Introduction to Reinforcement Learning, Internet: http://lslwww.epfl.ch/~aperez/RL/RL.html (accessed: October 2003)
Prez-Uribe, A., Sanchez, E.: Blackjack as a Test-bed for Learning Strategies in Neural Networks, Citeseer (1998), http://citeseer.nj.nec.com/40738.html (accessed: October 2003)
Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Inc., Englewood Cliffs (2003)
Sen, S., Weiss, G.: Learning in Multiagent Systems. In: Weiss, G. (ed.) Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence, MIT Press, Cambridge (1999)
Sian, S.S.: Extending Learning to Multiple Agents: Issues and a Model for Muli-agent Machine learning. In: Kodratoff, Y. (ed.) EWSL 1991. LNCS, vol. 482, pp. 440–456. Springer, Heidelberg (1991)
Silver, B., Frawley, Iba, G., Vittal, J., Bradford, K.: A Framework for Multiparadigmatic. In: Proceedings of the Seventh International Conference on Machine Learning, Austin, Texas, pp. 348–358 (1991)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, Adaptive Computation and Machine Learning, Cambridge, Mass., pp. 291–312 (1998)
Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative learning. In: Huhns, M.N., Singh, M.P. (eds.) Readings in Agents, pp. 487–494. Morgan Kaufmann, San Francisco (1997)
Weiss, G.: Learning to Coordinate Actions in Multi-agent Systems. In: Proceedings of the 13th International Joint Conference on Artificial Intelligence, pp. 311–316 (1993)
Whitehead, S.D.: A complexity Analysis of Cooperative Mechanisms in Reinforcement Learning. In: American Association for Artificial Intelligence’, pp. 607–613 (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shakshuki, E., Rahim, K. (2004). Multiple Reinforcement Learning Agents in a Static Environment. In: Orchard, B., Yang, C., Ali, M. (eds) Innovations in Applied Artificial Intelligence. IEA/AIE 2004. Lecture Notes in Computer Science(), vol 3029. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24677-0_102
Download citation
DOI: https://doi.org/10.1007/978-3-540-24677-0_102
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22007-7
Online ISBN: 978-3-540-24677-0
eBook Packages: Springer Book Archive