Settling the sample complexity of online reinforcement learning.
Zihan ZhangYuxin ChenJason D. LeeSimon S. DuPublished in: COLT (2024)
Keyphrases
- reinforcement learning
- online learning
- function approximation
- learning algorithm
- databases
- neural network
- artificial intelligence
- data sets
- artificial neural networks
- robot control
- dynamic programming
- robotic control
- temporal difference learning
- reinforcement learning algorithms
- temporal difference
- markov decision processes
- transfer learning
- supervised learning
- least squares
- mobile robot
- learning process
- machine learning
- real world