Robust Batch Policy Learning in Markov Decision Processes.
Zhengling QiPeng LiaoPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- partially observable
- state space
- policy iteration
- model based reinforcement learning
- continuous state spaces
- average reward
- learning algorithm
- average cost
- infinite horizon
- markov games
- planning under uncertainty
- action space
- action selection
- stochastic games
- finite state
- decision processes
- partially observable markov decision processes
- continuous state
- policy evaluation
- dynamic programming
- factored mdps
- reward function
- multi agent
- transition matrices
- real time dynamic programming