A Bayesian Approach to Imitation in Reinforcement Learning

Price, Bob; Boutilier, Craig

A Bayesian Approach to Imitation in Reinforcement Learning

Download BibTeX Cite

Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 712-719.

Abstract

In multiagent environments, forms of social learning such as teaching and imitation have been shown to aid the transfer of knowledge from experts to learners in reinforcement learning (RL ). We recast the problem of imitation in a Bayesian framework . Our Bayesian imitation model allows a learner to smoothly pool prior knowledge, data obtained through interaction with the environment, and information inferred from observations of expert agent behaviors. Our model integrates well with recent Bayesian exploration techniques, and can be readily generalized to new settings.

Bob Price, and Craig Boutilier. 2003. A Bayesian Approach to Imitation in Reinforcement Learning. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03. IJCAI, 712–719. https://ijcai.org/proceedings/2003/104

@inproceedings{ijcai2003p104,
  title     = {A Bayesian Approach to Imitation in Reinforcement Learning},
  author    = {Price, Bob and Boutilier, Craig},
  booktitle = {Proceedings of the Eighteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-03}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Georg Gottlob},
  pages     = {712--719},
  year      = {2003},
  url       = {https://ijcai.org/proceedings/2003/104},
}

TY  - CPAPER
TI  - A Bayesian Approach to Imitation in Reinforcement Learning
AU  - Price, Bob
AU  - Boutilier, Craig
T2  - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2003
SP  - 712
EP  - 719
UR  - https://ijcai.org/proceedings/2003/104
ER  -