POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis.
Weichao MaoKaiqing ZhangQiaomin XieTamer BasarPublished in: NeurIPS (2020)
Keyphrases
- monte carlo
- asymptotic analysis
- continuous space
- discrete space
- policy evaluation
- markov decision processes
- fluid model
- markov chain
- monte carlo simulation
- importance sampling
- reinforcement learning
- markov decision problems
- initial state
- particle filter
- monte carlo tree search
- variance reduction
- game tree
- temporal difference
- state space
- average reward
- mathematical morphology
- optimal policy
- search algorithm