Eliciting Additive Reward Functions for Markov Decision Processes

Regan, Kevin; Boutilier, Craig

doi:10.5591/978-1-57735-516-8/IJCAI11-360

Eliciting Additive Reward Functions for Markov Decision Processes

Kevin Regan, Craig Boutilier

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2159-2163.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-360

Abstract

Specifying the reward function of a Markov decision process (MDP) can be demanding, requiring human assessment of the precise quality of, and tradeoffs among, various states and actions. However, reward functions often possess considerable structure which can be leveraged to streamline their specification. We develop new, decision-theoretically sound heuristics for eliciting rewards for factored MDPs whose reward functions exhibit additive independence. Since we can often find good policies without complete reward specification, we also develop new (exact and approximate) algorithms for robust optimization ofimprecise-reward MDPs with such additive reward. Our methods are evaluated in two domains: autonomic computing and assistive technology.

Kevin Regan, and Craig Boutilier. 2011. Eliciting Additive Reward Functions for Markov Decision Processes. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 2159–2163. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-360

@inproceedings{ijcai2011p360,
  title     = {Eliciting Additive Reward Functions for Markov Decision Processes},
  author    = {Regan, Kevin and Boutilier, Craig},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {2159--2163},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-360},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-360},
}

TY  - CPAPER
TI  - Eliciting Additive Reward Functions for Markov Decision Processes
AU  - Regan, Kevin
AU  - Boutilier, Craig
T2  - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11
PB  - AAAI Press/International Joint Conferences on Artificial Intelligence
PY  - 2011
SP  - 2159
EP  - 2163
DO  - 10.5591/978-1-57735-516-8/IJCAI11-360
UR  - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-360
ER  -