Strategy Synthesis in Markov Decision Processes Under Limited Sampling Access.
Christel BaierClemens DubslaffPatrick WienhöftStefan J. KiebelPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- transition matrices
- reinforcement learning
- model based reinforcement learning
- policy iteration
- risk sensitive
- finite horizon
- dynamic programming
- decision theoretic planning
- partially observable
- markov decision process
- average reward
- infinite horizon
- sample size
- optimal strategy
- planning under uncertainty
- factored mdps
- reachability analysis
- action sets
- decision processes
- semi markov decision processes
- state and action spaces
- monte carlo
- interval estimation
- linear programming
- average cost
- learning rate
- action space
- reinforcement learning algorithms
- learning algorithm