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