Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis.
Gang WangSongtao LuGeorgios B. GiannakisGerald TesauroJian SunPublished in: NeurIPS (2020)
Keyphrases
- action space
- reinforcement learning
- function approximation
- function approximators
- markov decision processes
- temporal difference
- temporal difference learning algorithms
- temporal difference learning
- model free
- multi agent
- td learning
- feature extraction
- pattern recognition
- support vector
- learning tasks
- learning environment
- finite number
- machine learning
- temporal difference methods
- neural network