Symbolic Algorithms for Qualitative Analysis of Markov Decision Processes with Büchi Objectives.
Krishnendu ChatterjeeMonika HenzingerManas JoglekarNisarg ShahPublished in: CAV (2011)
Keyphrases
- markov decision processes
- qualitative analysis
- policy iteration
- quantitative analysis
- factored mdps
- state space
- reachability analysis
- learning algorithm
- reinforcement learning
- action sets
- finite state
- optimal policy
- finite horizon
- planning under uncertainty
- computational complexity
- transition matrices
- reinforcement learning algorithms
- markov decision process
- least squares
- dynamic programming
- np hard