Non-stationary Reinforcement Learning under General Function Approximation.
Songtao FengMing YinRuiquan HuangYu-Xiang WangJing YangYingbin LiangPublished in: ICML (2023)
Keyphrases
- function approximation
- non stationary
- reinforcement learning
- temporal difference
- temporal difference learning
- temporal difference learning algorithms
- mountain car
- random fields
- model free
- function approximators
- radial basis function
- learning tasks
- state space
- td learning
- reinforcement learning algorithms
- learning algorithm
- pattern recognition
- machine learning
- neural network
- empirical mode decomposition
- markov decision process
- optimal control
- e learning
- optimal policy
- collaborative filtering