Learning Weighted Assumptions for Compositional Verification of Markov Decision Processes.
Fei HeXiaowei GaoMiaofei WangBow-Yaw WangLijun ZhangPublished in: ACM Trans. Softw. Eng. Methodol. (2016)
Keyphrases
- markov decision processes
- reinforcement learning
- learning algorithm
- state space
- real time dynamic programming
- model based reinforcement learning
- partially observable
- finite horizon
- linear programming
- supervised learning
- stochastic games
- optimal policy
- finite state
- policy iteration
- macro actions
- reachability analysis
- dynamic programming
- transition matrices
- data mining