Minimax Regret for Stochastic Shortest Path.
Alon CohenYonathan EfroniYishay MansourAviv RosenbergPublished in: NeurIPS (2021)
Keyphrases
- minimax regret
- stochastic shortest path
- markov decision processes
- preference elicitation
- utility function
- reward function
- decision problems
- markov decision problems
- stochastic programming
- optimal policy
- misclassification costs
- partially observable
- reinforcement learning
- cost sensitive
- multiple agents
- training data
- expected utility
- supervised learning
- training and test data
- special case