A Theory of Regularized Markov Decision Processes.
Matthieu GeistBruno ScherrerOlivier PietquinPublished in: CoRR (2019)
Keyphrases
- action sets
- markov decision processes
- finite state
- reinforcement learning
- state space
- optimal policy
- policy iteration
- decision theoretic planning
- average cost
- planning under uncertainty
- dynamic programming
- risk sensitive
- decision processes
- least squares
- reachability analysis
- transition matrices
- reinforcement learning algorithms
- decision problems
- machine learning
- markov decision process
- partially observable
- finite horizon
- data mining
- finite number
- planning problems
- factored mdps
- optimal solution
- objective function
- model based reinforcement learning