A Reinforcement Learning Model Based on Temporal Difference Algorithm.
Xiali LiZhengyu LvSong WangZhi WeiLicheng WuPublished in: IEEE Access (2019)
Keyphrases
- reinforcement learning
- model free
- temporal difference
- learning algorithm
- td learning
- function approximation
- dynamic programming
- actor critic
- optimization algorithm
- temporal difference learning
- cost function
- supervised learning
- convergence rate
- policy iteration
- evaluation function
- neural network
- policy evaluation
- reinforcement learning algorithms
- decision making
- training data
- objective function
- monte carlo
- state space
- search space