Compositional Reasoning for Interval Markov Decision Processes.
Vahid HashemiHolger HermannsAndrea TurriniPublished in: CoRR (2016)
Keyphrases
- markov decision processes
- state space
- optimal policy
- transition matrices
- finite state
- policy iteration
- reinforcement learning
- reachability analysis
- dynamic programming
- decision theoretic planning
- finite horizon
- infinite horizon
- reinforcement learning algorithms
- factored mdps
- knowledge base
- risk sensitive
- decision processes
- average reward
- planning under uncertainty
- markov decision process
- average cost
- action space
- state and action spaces
- markov decision problems
- probabilistic planning
- action sets
- reasoning process
- model based reinforcement learning
- decision problems