Stable Training of Bellman Error in Reinforcement Learning.
Chen GongYunpeng BaiXinwen HouXiaohui JiPublished in: ICONIP (5) (2020)
Keyphrases
- reinforcement learning
- supervised learning
- error rate
- function approximation
- test set
- temporal difference learning
- learning algorithm
- training algorithm
- training examples
- model free
- piecewise linear
- linear program
- training samples
- training error
- training set
- actor critic
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- robotic control
- generalization error
- data sets
- dynamic programming
- learning process
- machine learning
- neural network