Reinforcement Learning Based Monte Carlo Tree Search for Temporal Path Discovery.
Pengfei DingGuanfeng LiuPengpeng ZhaoAn LiuZhixu LiKai ZhengPublished in: ICDM (2019)
Keyphrases
- monte carlo tree search
- reinforcement learning
- temporal difference
- bayesian reinforcement learning
- monte carlo
- reinforcement learning methods
- temporal difference learning
- tree search algorithm
- evaluation function
- temporal information
- function approximation
- optimal policy
- temporal constraints
- reinforcement learning algorithms
- state space
- model free
- game tree
- temporal reasoning
- markov decision processes
- shortest path
- monte carlo search
- learning process
- control problems
- markov decision process
- path finding
- optimal path
- adaptive control
- step size
- dynamical systems
- transfer learning
- alpha beta search