ABSTRACT
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advice-taking mechanisms. We discuss the importance of transfer in complex domains such as RoboCup soccer, and show how to use automatically generated advice to perform transfer.
- N. Lavrac and S. Dzeroski. Inductive Logic Programming. Ellis Horwood, New York, 1994.Google Scholar
- R. Maclin, J. Shavlik, L. Torrey, T. Walker, and E. Wild. Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In AAAI, 2005. Google ScholarDigital Library
- P. Stone and R. Sutton. Scaling reinforcement learning toward RoboCup soccer. In ICML, 2001. Google ScholarDigital Library
- L. Torrey, J. Shavlik, T. Walker, and R. Maclin. Using advice to transfer knowledge acquired in one reinforcement learning task to another. In ECML, 2005. Google ScholarDigital Library
Index Terms
- Knowledge transfer via advice taking
Recommendations
Enhancing knowledge base with knowledge transfer
SIGIR '12: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrievalA Knowledge Base (KB) stores, organizes, and shares information pertinent to entities (i.e. KB nodes) such as people, organizations, and events. A large KB system, such as Wikipedia, relies on human curators to create and maintain the content in the ...
Object-Focused Advice in Reinforcement Learning
AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent SystemsIn order for robots and intelligent agents to interact with and learn from people with no machine-learning expertise, robots should be able to learn from natural human instruction. Many human explanations consist of simple sentences without state ...
Skill acquisition via transfer learning and advice taking
ECML'06: Proceedings of the 17th European conference on Machine LearningWe describe a reinforcement learning system that transfers skills from a previously learned source task to a related target task. The system uses inductive logic programming to analyze experience in the source task, and transfers rules for when to take ...
Comments