Commitment Semantics for Sequential Decision Making under Reward Uncertainty
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 3315-3322.
Abstract
Cooperating agents can make commitments to help each other, but commitments might have to be probabilistic when actions have stochastic outcomes. We consider the additional complication in cases where an agent might prefer to change its policy as it learns more about its reward function from experience. How should such an agent be allowed to change its policy while still faithfully pursuing its commitment in a principled decision-theoretic manner? We address this question by defining a class of Dec-POMDPs with Bayesian reward uncertainty, and by developing a novel Commitment Constrained Iterative Mean Reward algorithm that implements the semantics of faithful commitment pursuit while still permitting the agent's response to the evolving understanding of its rewards. We bound the performance of our algorithm theoretically, and evaluate empirically how it effectively balances solution quality and computation cost.
@inproceedings{ijcai2016p469,
title = {Commitment Semantics for Sequential Decision Making under Reward Uncertainty},
author = {Zhang, Qi and Durfee, Edmund H. and Singh, Satinder and Chen, Anna and Witwicki, Stefan J.},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {3315--3322},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/469},
}
TY - CPAPER TI - Commitment Semantics for Sequential Decision Making under Reward Uncertainty AU - Zhang, Qi AU - Durfee, Edmund H. AU - Singh, Satinder AU - Chen, Anna AU - Witwicki, Stefan J. T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 3315 EP - 3322 UR - https://ijcai.org/proceedings/2016/469 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: