Minimizing Maximum Regret in Commitment Constrained Sequential Decision Making.
Qi ZhangSatinder P. SinghEdmund H. DurfeePublished in: CoRR (2017)
Keyphrases
- sequential decision making
- decision problems
- reinforcement learning
- interactive dynamic influence diagrams
- influence diagrams
- temporal difference
- online learning
- lower bound
- expected utility
- worst case
- computational complexity
- decision making
- data mining
- neural network
- active learning
- game theory
- pairwise
- training set
- reinforcement learning algorithms