Compositional Reasoning for Markov Decision Processes - (Extended Abstract).
Yuxin DengMatthew HennessyPublished in: FSEN (2011)
Keyphrases
- extended abstract
- markov decision processes
- optimal policy
- state space
- decision theoretic planning
- finite state
- transition matrices
- policy iteration
- reachability analysis
- infinite horizon
- planning under uncertainty
- reinforcement learning
- reinforcement learning algorithms
- dynamic programming
- average cost
- finite horizon
- action space
- reasoning process
- partially observable
- risk sensitive
- factored mdps
- state and action spaces
- markov decision process
- model based reinforcement learning
- reward function
- semi markov decision processes
- knowledge base
- decision making
- sufficient conditions
- state abstraction
- decision processes
- machine learning