Permissive Supervisor Synthesis for Markov Decision Processes through Learning.
Bo WuXiaobin ZhangHai LinPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- reinforcement learning
- stochastic games
- model based reinforcement learning
- state space
- learning algorithm
- optimal policy
- supervised learning
- finite state
- dynamic programming
- macro actions
- policy iteration
- real time dynamic programming
- semi markov decision processes
- state abstraction
- risk sensitive
- learning tasks
- linear program
- sufficient conditions
- linear programming