Robustness to Modeling Errors in Risk-Sensitive Markov Decision Problems with Markov Risk Measures.
Shiping ShaoAbhishek GuptaWilliam B. HaskellPublished in: CoRR (2022)
Keyphrases
- markov decision problems
- linear programming
- partially observable
- state space
- transition probabilities
- decision theoretic
- markov chain
- reinforcement learning
- optimal policy
- utility function
- markov decision processes
- dynamic programming
- evolutionary algorithm
- machine learning
- average cost
- decision processes
- artificial intelligence
- linear program
- supervised learning
- policy iteration
- action space