Abstract
During the learning process, every agent’s action affects the interaction with the environment based on the agent’s current knowledge and future knowledge. The agent must therefore have to choose between exploiting its current knowledge or exploring other alternatives to improve its knowledge for better decisions in the future. This paper presents critical analysis on a number of exploration strategies reported in the open literatures. Exploration strategies namely random search, greedy, ε-greedy, Boltzmann Distribution (BD), Simulated Annealing (SA), Probability Matching (PM) and Optimistic Initial Values (OIV) are implemented to study on their performances on a multi-agent foraging task modeled.
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
Carmel, D., Markovitch, S.: Exploration strategies for model-based learning in multi-agent systems: Exploration strategies. Autonomous Agents and Multi-agent Systems 2(2), 141–172 (1999)
Even-Dar, E., Mansour, Y.: Convergence of optimistic and incremental Q-learning. Advances in Neural Information Processing Systems 2, 1499–1506 (2002)
Guo, M., Liu, Y., Malec, J.: A new Q-learning algorithm based on the metropolis criterion. IEEE Transactions On Systems, Man, And Cybernetics? Part B: Cybernetics 34(5), 2141 (2004)
Koulouriotis, D.E., Xanthopoulos, A.: Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems. Applied Mathematics and Computation 196(2), 913–922 (2008)
Morihiro, K., Isokawa, T., Nishimura, H., Matsui, N.: Emergence of Flocking Behavior Based on Reinforcement Learning. In: Gabrys, B., Howlett, R.J., Jain, L.C. (eds.) KES 2006. LNCS (LNAI), vol. 4253, pp. 699–706. Springer, Heidelberg (2006)
Price, B., Boutilier, C.: Accelerating reinforcement learning through implicit imitation. Journal of Artificial Intelligence Research 19(1), 569–629 (2003)
Strehl, A., Li, L., Wiewiora, E., Langford, J., Littman, M.: PAC model-free reinforcement learning. In: Proceedings of the 23rd International Conference on Machine Learning, p. 888. ACM (2006)
Sutton, R., Barto, A.: Reinforcement learning: An introduction. The MIT Press (1998)
Szita, I., Lőrincz, A.: The many faces of optimism: a unifying approach. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1048–1055. ACM (2008)
Webots: http://www.cyberbotics.com, http://www.cyberbotics.com , commercial Mobile Robot Simulation Software
Whiteson, S., Taylor, M., Stone, P.: Empirical studies in action selection with reinforcement learning. Adaptive Behavior 15(1), 33 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mohan, Y., S.G., P. (2011). Exploration Strategies for Learning in Multi-agent Foraging. In: Panigrahi, B.K., Suganthan, P.N., Das, S., Satapathy, S.C. (eds) Swarm, Evolutionary, and Memetic Computing. SEMCCO 2011. Lecture Notes in Computer Science, vol 7077. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27242-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-27242-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27241-7
Online ISBN: 978-3-642-27242-4
eBook Packages: Computer ScienceComputer Science (R0)