On Gap-dependent Bounds for Offline Reinforcement Learning.
Xinqi WangQiwen CuiSimon S. DuPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- upper bound
- function approximation
- worst case
- model free
- upper and lower bounds
- lower bound
- reinforcement learning algorithms
- state space
- markov decision processes
- real time
- markov decision process
- tight bounds
- machine learning
- worst case bounds
- autonomous learning
- robotic control
- lower and upper bounds
- learning problems
- dynamic programming
- learning algorithm
- optimal control
- reward function
- optimal policy
- action space
- function approximators
- temporal difference learning
- reinforcement learning methods
- learning process
- multi agent reinforcement learning
- genetic algorithm