Schedule Extra Train(s) into Existing Timetable Using Actor-Critic Reinforcement Learning.
Jin LiuRonghui LiuPublished in: ITSC (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- round robin tournament
- approximate dynamic programming
- optimal control
- reinforcement learning algorithms
- neuro fuzzy
- function approximation
- gradient method
- policy iteration
- state space
- markov decision processes
- model free
- control problems
- policy gradient methods
- least squares
- step size
- natural actor critic
- multi agent
- linear program
- transfer learning
- optimal policy
- convergence rate
- control policy
- average reward
- supervised learning
- evolutionary algorithm