Belief State Monte Carlo Planning for Multi-agent Visibility-Based Pursuit-Evasion.
Xiao XuShengming GuoDong LiPinggang YuXiaocheng LiuYi RenPublished in: AsiaSim (2) (2022)
Keyphrases
- monte carlo
- belief state
- pursuit evasion
- multi agent
- partially observable markov decision processes
- belief space
- state space
- partial observability
- markov chain
- partially observable
- belief revision
- partially observable markov decision process
- monte carlo simulation
- planning under uncertainty
- reactive planning
- importance sampling
- reinforcement learning
- particle filter
- monte carlo tree search
- single agent
- point based value iteration
- adaptive sampling
- planning problems
- heuristic search
- dynamic bayesian networks
- matrix inversion
- markovian decision
- markov random field
- dynamic programming
- temporal difference
- multiple agents