Bayes-CPACE: PAC Optimal Exploration in Continuous Space Bayes-Adaptive Markov Decision Processes.
Gilwoo LeeSanjiban ChoudhuryBrian HouSiddhartha S. SrinivasaPublished in: CoRR (2018)
Keyphrases
- interval estimation
- markov decision processes
- continuous space
- dynamic programming
- collaborative filtering
- average cost
- optimal policy
- action sets
- finite horizon
- average reward
- reinforcement learning
- state space
- policy iteration
- discrete space
- model based reinforcement learning
- decision theoretic planning
- transition matrices
- finite state
- planning under uncertainty
- stationary policies
- total reward
- discounted reward
- infinite horizon
- learning algorithm
- reachability analysis
- mathematical morphology
- optimal control
- action space