Monte Carlo Tree Search with State Merging for Reinforcement Learning in Regular Decision Processes (Short paper).
Gabriel Paludo LicksPublished in: DC@AI*IA (2023)
Keyphrases
- decision processes
- reinforcement learning
- monte carlo tree search
- markov decision processes
- state space
- reinforcement learning methods
- temporal difference learning
- monte carlo
- decision problems
- decision process
- bayesian reinforcement learning
- reinforcement learning algorithms
- temporal difference
- evaluation function
- action selection
- optimal policy
- multi agent
- function approximation
- control problems
- domain knowledge
- expert systems
- decision making