Energy and Mean-Payoff Parity Markov Decision Processes.
Krishnendu ChatterjeeLaurent DoyenPublished in: MFCS (2011)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- reinforcement learning
- transition matrices
- policy iteration
- dynamic programming
- reachability analysis
- state and action spaces
- average reward
- decision theoretic planning
- infinite horizon
- average cost
- stochastic games
- model based reinforcement learning
- markov decision process
- finite horizon
- factored mdps
- decision processes
- planning under uncertainty
- game theory
- action space
- reinforcement learning algorithms
- risk sensitive
- discounted reward
- semi markov decision processes
- markov chain
- data mining