On Gap-dependent Bounds for Offline Reinforcement Learning.
Xinqi WangQiwen CuiSimon S. DuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- lower bound
- upper bound
- function approximation
- learning algorithm
- multi agent
- model free
- state space
- lower and upper bounds
- worst case
- machine learning
- reinforcement learning algorithms
- temporal difference
- error bounds
- genetic algorithm
- real time
- average case
- confidence bounds
- optimal control
- support vector machine
- dynamic programming
- autonomous learning
- robotic control
- worst case bounds