Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Algorithms for Inverse Reinforcement Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Algorithms for partially observable markov decision processes
Algorithms for partially observable markov decision processes
Mathematics of Operations Research
Robust Control of Markov Decision Processes with Uncertain Transition Matrices
Operations Research
Proceedings of the 24th international conference on Machine learning
Solving transition independent decentralized Markov decision processes
Journal of Artificial Intelligence Research
A bilinear programming approach for multiagent planning
Journal of Artificial Intelligence Research
Constraint-based optimization and utility elicitation using the minimax decision criterion
Artificial Intelligence
Regret-based reward elicitation for Markov decision processes
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
IEEE Transactions on Information Technology in Biomedicine
Eliciting additive reward functions for Markov decision processes
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
People, sensors, decisions: Customizable and adaptive technologies for assistance in healthcare
ACM Transactions on Interactive Intelligent Systems (TiiS) - Special issue on highlights of the decade in interactive intelligent systems
Interactive value iteration for Markov decision processes with unknown rewards
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
| Hi-index | 0.00 |
Imprecise-reward Markov decision processes (IRMDPs) are MDPs in which the reward function is only partially specified (e.g., by some elicitation process). Recent work using minimax regret to solve IRMDPs has shown, despite their theoretical intractability, how the set of policies that are nondominated w.r.t. reward uncertainty can be exploited to accelerate regret computation. However, the number of nondominated policies is generally so large as to undermine this leverage. In this paper, we show how the quality of the approximation can be improved online by pruning/adding nondominated policies during reward elicitation, while maintaining computational tractability. Drawing insights from the POMDP literature, we also develop a new anytime algorithm for constructing the set of nondominated policies with provable (anytime) error bounds. These bounds can be exploited to great effect in our online approximation scheme.