Efficient Strategy Iteration for Mean Payoff in Markov Decision Processes.
Jan KretínskýTobias MeggendorferPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- decision theoretic planning
- reinforcement learning algorithms
- transition matrices
- policy iteration
- reachability analysis
- planning under uncertainty
- model based reinforcement learning
- markov decision process
- risk sensitive
- infinite horizon
- machine learning
- game theory
- state and action spaces
- average reward
- decision processes
- action space
- average cost
- optimal solution
- markov chain
- partially observable
- dynamical systems