The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation.
Noah GolowichAnkur MoitraPublished in: CoRR (2024)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference learning
- temporal difference
- mountain car
- model free
- state action
- reinforcement learning algorithms
- learning tasks
- radial basis function
- linear program
- state space
- transfer learning
- supervised learning
- genetic algorithm
- neural network
- knn
- learning algorithm
- td learning
- machine learning