Synthesis for PCTL in Parametric Markov Decision Processes.
Ernst Moritz HahnTingting HanLijun ZhangPublished in: NASA Formal Methods (2011)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- reinforcement learning
- policy iteration
- dynamic programming
- transition matrices
- infinite horizon
- finite horizon
- risk sensitive
- reinforcement learning algorithms
- reachability analysis
- decision theoretic planning
- average cost
- decision processes
- model based reinforcement learning
- average reward
- planning under uncertainty
- partially observable
- decision problems
- semi markov decision processes
- markov decision process
- action sets
- factored mdps
- policy evaluation