Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism.
Wang Chi CheungDavid Simchi-LeviRuihao ZhuPublished in: CoRR (2020)
Keyphrases
- non stationary
- markov decision processes
- reinforcement learning
- optimal policy
- state space
- policy iteration
- reinforcement learning algorithms
- finite state
- state and action spaces
- dynamic programming
- action space
- model based reinforcement learning
- average reward
- partially observable
- transition matrices
- decision theoretic planning
- average cost
- infinite horizon
- random fields
- reachability analysis
- finite horizon
- markov decision process
- model free
- planning under uncertainty
- policy evaluation
- factored mdps
- action sets
- multi agent
- machine learning
- reward function
- learning algorithm
- decentralized control
- hidden markov models
- total reward
- stochastic games
- function approximation
- temporal difference