Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding.
Alexey SkrynnikAnton AndreychukKonstantin S. YakovlevAleksandr PanovPublished in: CoRR (2023)
Keyphrases
- partially observable
- path finding
- monte carlo tree search
- multi agent
- reinforcement learning
- monte carlo
- temporal difference
- state space
- heuristic search
- decision problems
- single agent
- path planning
- markov decision processes
- dynamical systems
- evaluation function
- search algorithm
- markov decision problems
- infinite horizon
- belief state
- multiple agents
- reward function
- multi agent systems
- reinforcement learning algorithms
- optimal path
- model free
- hill climbing
- markov chain
- function approximation
- dynamic programming
- machine learning
- game tree
- learning algorithm
- mobile robot
- planning domains
- rule learning
- supervised learning
- orders of magnitude