BriefGPT.xyz
Oct, 2019
度量空间中的情节式强化学习自适应离散化
Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
HTML
PDF
Sean R. Sinclair, Siddhartha Banerjee, Christina Lee Yu
TL;DR
提出了一种基于自适应数据驱动离散化的$Q$-学习策略的高效算法，可以用于大型（可能是连续的）状态-动作空间的无模型经验强化学习。
Abstract
We present an efficient algorithm for model-free episodic
reinforcement learning
on large (potentially continuous) state-action spaces. Our algorithm is based on a novel
q-learning
policy with adaptive
→