强化学习中的迁移:方法和进展

Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty[J] . Michael G. Madden,Tom Howley.Artificial Intelligence Review . 2004 (3)

Proto-value functions:developmental reinforce-ment learning .2 Mahadevan S. Proceedings of the Twenty-second Interna-tional Conference on Machine Learning . 2005

Improving actionselectionin MDP’svia knowledge transfer .2 Sherstove A A,Stone P. Proceedings of the Twentieth Na-tional Conference on Artificial Intelligence . 2005

Autonomous transfer forreinforcement learning .2 Taylor M E,Kuhlmann G,Stone P. Proceedings of the SeventeenthInternational Conference on Autonomous Agents and Multi-A-gent Systems . 2008

Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty[J] . Michael G. Madden,Tom Howley.Artificial Intelligence Review . 2004 (3)

Proto-value functions:developmental reinforce-ment learning .2 Mahadevan S. Proceedings of the Twenty-second Interna-tional Conference on Machine Learning . 2005

Improving actionselectionin MDP’svia knowledge transfer .2 Sherstove A A,Stone P. Proceedings of the Twentieth Na-tional Conference on Artificial Intelligence . 2005

Autonomous transfer forreinforcement learning .2 Taylor M E,Kuhlmann G,Stone P. Proceedings of the SeventeenthInternational Conference on Autonomous Agents and Multi-A-gent Systems . 2008