Blackwell Online Learning for Markov Decision Processes.
Tao LiGuanze PengQuanyan ZhuPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- online learning
- optimal policy
- state space
- finite state
- transition matrices
- decision theoretic planning
- dynamic programming
- reinforcement learning
- policy iteration
- finite horizon
- active learning
- e learning
- decision processes
- planning under uncertainty
- factored mdps
- reinforcement learning algorithms
- average cost
- reachability analysis
- risk sensitive
- partially observable
- model based reinforcement learning
- action sets
- markov decision process
- reward function
- infinite horizon
- machine learning
- average reward
- data mining
- action space
- linear programming
- search algorithm
- stochastic shortest path