Non-stationary Reinforcement Learning under General Function Approximation.
Songtao FengMing YinRuiquan HuangYu-Xiang WangJing YangYingbin LiangPublished in: CoRR (2023)
Keyphrases
- function approximation
- non stationary
- reinforcement learning
- model free
- temporal difference learning algorithms
- temporal difference
- temporal difference learning
- radial basis function
- reinforcement learning algorithms
- learning tasks
- markov decision processes
- function approximators
- empirical mode decomposition
- mountain car
- state space
- machine learning
- supervised learning
- optimal policy
- random fields
- optimal control
- feature vectors
- genetic algorithm