Quantile Markov Decision Process.
Xiaocheng LiHuaiyang ZhongMargaret L. BrandeauPublished in: CoRR (2017)
Keyphrases
- markov decision process
- state space
- markov decision processes
- reinforcement learning
- optimal policy
- infinite horizon
- temporal difference learning
- transition matrices
- finite horizon
- initial state
- partial observability
- policy iteration
- transition probabilities
- search engine
- multiagent systems
- average cost
- linear programming
- dynamic programming
- multi agent