Robust Entropy-regularized Markov Decision Processes.
Tien MaiPatrick JailletPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- dynamic programming
- finite state
- state space
- policy iteration
- decision theoretic planning
- planning under uncertainty
- action space
- finite horizon
- model based reinforcement learning
- transition matrices
- action sets
- partially observable
- risk sensitive
- average cost
- infinite horizon
- reinforcement learning algorithms
- reachability analysis
- markov decision process
- average reward
- decision processes
- data mining
- state and action spaces
- reward function
- objective function
- real valued
- semi markov decision processes
- multi agent
- interval estimation