Faster Algorithms for Markov Decision Processes with Low Treewidth.
Krishnendu ChatterjeeJakub LackiPublished in: CAV (2013)
Keyphrases
- markov decision processes
- policy iteration
- factored mdps
- reinforcement learning
- state space
- optimal policy
- finite state
- transition matrices
- planning under uncertainty
- markov decision process
- average cost
- reinforcement learning algorithms
- space complexity
- dynamic programming
- finite horizon
- action space
- heuristic search
- decision theoretic planning
- semi markov decision processes
- model based reinforcement learning
- machine learning