An Efficient Solution to s-Rectangular Robust Markov Decision Processes.
Navdeep KumarKfir LevyKaixin WangShie MannorPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- reinforcement learning
- decision theoretic planning
- dynamic programming
- transition matrices
- reachability analysis
- reinforcement learning algorithms
- finite horizon
- partially observable
- average cost
- factored mdps
- model based reinforcement learning
- state and action spaces
- infinite horizon
- markov decision process
- decision processes
- planning under uncertainty
- risk sensitive
- policy iteration
- robust optimization
- semi markov decision processes
- search algorithm
- markov chain
- expected reward
- action sets
- discounted reward
- decision makers
- least squares