Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Scaling Reinforcement Learning toward RoboCup Soccer
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty
Artificial Intelligence Review
Machine Learning
Probabilistic policy reuse in a reinforcement learning agent
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Logical and Relational Learning: From ILP to MRDM (Cognitive Technologies)
Logical and Relational Learning: From ILP to MRDM (Cognitive Technologies)
Efficient Weight Learning for Markov Logic Networks
PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases
Learning relational options for inductive transfer in relational reinforcement learning
ILP'07 Proceedings of the 17th international conference on Inductive logic programming
| Hi-index | 0.00 |
We propose using a statistical-relational model, the Markov Logic Network, for knowledge transfer in reinforcement learning. Our goal is to extract relational knowledge from a source task and use it to speed up learning in a related target task. We show that Markov Logic Networks are effective models for capturing both source-task Q-functions and source-task policies. We apply them via demonstration, which involves using them for decision making in an initial stage of the target task before continuing to learn. Through experiments in the RoboCup simulated-soccer domain, we show that transfer via Markov Logic Networks can significantly improve early performance in complex tasks, and that transferring policies is more effective than transferring Q-functions.