One-Counter Markov Decision Processes
Tomás BrázdilVáclav BrozekKousha EtessamiAntonín KuceraDominik WojtczakPublished in: CoRR (2009)
Keyphrases
- markov decision processes
- finite state
- state space
- reinforcement learning
- optimal policy
- policy iteration
- dynamic programming
- decision theoretic planning
- transition matrices
- reachability analysis
- factored mdps
- partially observable
- average cost
- risk sensitive
- action space
- planning under uncertainty
- finite horizon
- average reward
- reinforcement learning algorithms
- model based reinforcement learning
- decision diagrams
- state and action spaces
- discounted reward
- decision processes
- policy evaluation
- markov decision process
- reward function
- infinite horizon
- real time dynamic programming