Monte Carlo Value Iteration for Continuous-State POMDPs.
Haoyu BaiDavid HsuWee Sun LeeNgo Anh VienPublished in: WAFR (2010)
Keyphrases
- monte carlo
- continuous state
- partially observable markov decision processes
- finite state
- markov chain
- reinforcement learning
- markov decision processes
- state space
- dynamical systems
- optimal policy
- belief state
- dynamic programming
- decision problems
- policy search
- belief space
- continuous action
- planning problems
- monte carlo methods
- steady state
- particle filter
- partially observable
- multi agent
- monte carlo tree search
- point based value iteration
- temporal difference
- robot navigation
- average reward
- infinite horizon
- heuristic search
- transition probabilities