Optimistic Thompson Sampling-based algorithms for episodic reinforcement learning.
Bingshan HuTianyue H. ZhangNidhi HegdeMark SchmidtPublished in: UAI (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- data structure
- computationally efficient
- recently developed
- database
- machine learning
- computational efficiency
- state space
- monte carlo
- orders of magnitude
- stochastic approximation
- data mining algorithms
- benchmark datasets
- machine learning algorithms
- computational cost
- significant improvement
- neural network