Relational reinforcement learning for agents in worlds with objects
January 2003
Pages 306 - 322
Abstract
In reinforcement learning, an agent tries to learn a policy, i.e., how to select an action in a given state of the environment, so that it maximizes the total amount of reward it receives when interacting with the environment. We argue that a relational representation of states is natural and useful when the environment is complex and involves many inter-related objects. Relational reinforcement learning works on such relational representations and can be used to approach problems that are currently out of reach for classical reinforcement learning approaches. This chapter introduces relational reinforcement learning and gives an overview of techniques, applications and recent developments in this area.
References
[1]
Bertsekas, D.P., & Tsitsiklis, J.N. (1996). Neuro-Dynamic Programming. Belmont, MA: Athena Scientific.
[2]
Blockeel, H., De Raedt, L., & Ramon, J. (1998). Top-down induction of clustering trees. In Proc. 15th International Conference on Machine Learning, pages 55-63. San Francisco: Morgan Kaufmann.
[3]
Chapman, D., & Kaelbling, L. P. (1991). Input generalization in delayed reinforcement learning: An algorithm and performance comparisons. In Proc. 12th International Joint Conference on Artificial Intelligence, pages 726-731. San Mateo, CA: Morgan Kaufmann.
[4]
Driessens, K., & Blockeel, H. (2001). Learning Digger using hierarchical reinforcement learning for concurrent goals. In Proc. 5th European Workshop on Reinforcement Learning, pages 11-12. Utrecht, The Netherlands: CKI Utrecht University.
[5]
Driessens, K., & Džeroski, S. (2002) Integrating experimentation and guidance in relational reinforcement learning. In Proc. 19th International Conference on Machine Learning, pages 115-122. San Francisco, CA: Morgan Kaufmann.
[6]
Driessens, K., Ramon, J., & Blockeel, H. (2001). Speeding up relational reinforcement learning through the use of an incremental first order decision tree algorithm. In Proc. 12th European Conference on Machine Learning, pages 97-108. Berlin: Springer.
[7]
Džeroski, S., De Raedt, L., & Blockeel, H. (1998). Relational reinforcement learning. In Proc. 15th International Conference on Machine Learning, pages 136-143. San Francisco, CA: Morgan Kaufmann.
[8]
Džeroski, S., De Raedt, L., & Driessens, K. (2001). Relational reinforcement learning. Machine Learning, 43, 7-52.
[9]
Kazakov, D., & Kudenko, D. (2001). Machine learning and inductive logic programming for multi-agent systems. In Luck, M., Marik, V., Stepankova, O., and Trappl, R., editors, Multi-Agent Systems and Applications, pages 246-270. Berlin: Springer.
[10]
Lavrač, N. and Džeroski, S. (1994). Inductive Logic Programming: Techniques and Applications., New York: Ellis Horwood. Freely available at http://www-ai.ijs.si/SasoDzeroski/ILPBook/
[11]
Smart, W. D., & Kaelbling, L. P. (2000). Practical reinforcement learning in continuous spaces. In Proc. 17th International Conference on Machine Learning, pages 903-910. San Francisco, CA: Morgan Kaufmann.
[12]
Sutton, R. S. (1996) Generalization in reinforcement learning: Successful examples using sparse coarse coding. In Proc. 8th Conference on Advances in Neural Information Processing Systems, pages 1038-1044. Cambridge, MA: MIT Press.
[13]
Sutton, R. S., & Barto, A. G. (1998). Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press.
- Relational reinforcement learning for agents in worlds with objects
Recommendations
Relational Reinforcement Learning
Relational reinforcement learning is presented, a learning technique that combines reinforcement learning with relational learning or inductive logic programming. Due to the use of a more expressive representation language to represent states, actions ...
Relational Reinforcement Learning
EASSS '01: Selected Tutorial Papers from the 9th ECCAI Advanced Course ACAI 2001 and Agent Link's 3rd European Agent Systems Summer School on Multi-Agent Systems and ApplicationsThis paper presents an introduction to reinforcement learning and relational reinforcement learning at a level to be understood by students and researchers with different backgrounds.It gives an overview of the fundamental principles and techniques of ...
Learning with whom to communicate using relational reinforcement learning
AAMAS '09: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2Relational reinforcement learning (RRL) has emerged in the machine learning community as a new promising subfield of reinforcement learning (RL) (e.g. [1]). It upgrades RL techniques by using relational representations for states, actions and learned ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 January 2003
Qualifiers
- Chapter
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 3Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Dec 2024