Toward General Function Approximation in Nonstationary Reinforcement Learning.
Songtao FengMing YinRuiquan HuangYu-Xiang WangJing YangYingbin LiangPublished in: IEEE J. Sel. Areas Inf. Theory (2024)
Keyphrases
- function approximation
- non stationary
- reinforcement learning
- temporal difference learning
- learning tasks
- function approximators
- temporal difference learning algorithms
- discrete valued
- temporal difference
- model free
- mountain car
- radial basis function
- reinforcement learning algorithms
- state space
- td learning
- random fields
- neural network
- transfer learning
- optimal policy
- multi agent
- genetic algorithm