Symbolic Algorithms for Graphs and Markov Decision Processes with Fairness Objectives.
Krishnendu ChatterjeeMonika HenzingerVeronika LoitzenbauerSimin OraeeViktor TomanPublished in: CAV (2) (2018)
Keyphrases
- markov decision processes
- policy iteration
- optimal policy
- factored mdps
- dynamic programming
- finite state
- state space
- reinforcement learning
- learning algorithm
- policy evaluation
- decision theoretic planning
- reachability analysis
- computational complexity
- multi agent
- decision processes
- average reward
- transition matrices