Decentralized Adaptive TD(λ) Learning With Linear Function Approximation: Nonasymptotic Analysis.
Junlong ZhuTao MaoMingchuan ZhangQuanbo GeQingtao WuKeqin LiPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- function approximation
- td learning
- temporal difference
- reinforcement learning
- temporal difference learning algorithms
- reinforcement learning algorithms
- learning tasks
- radial basis function
- model free
- search space
- function approximators
- pattern recognition
- text classification
- k nearest neighbor
- markov decision processes
- evaluation function
- active learning
- decision making