On the Statistical Efficiency of Mean Field Reinforcement Learning with General Function Approximation.
Jiawei HuangBatuhan YardimNiao HePublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- temporal difference learning
- radial basis function
- temporal difference learning algorithms
- mountain car
- learning tasks
- tile coding
- function approximators
- model free
- state action space
- learning algorithm
- reinforcement learning algorithms
- state space
- pairwise
- markov random field
- monte carlo
- support vector
- genetic algorithm
- machine learning