all AI news
Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
March 5, 2024, 2:45 p.m. | Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei
cs.LG updates on arXiv.org arxiv.org
Abstract: This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or incur high burn-in cost to reach sample optimality, thus posing an impediment to efficient offline RL in sample-starved applications.
We demonstrate that the model-based (or "plug-in") approach achieves minimax-optimal sample complexity without …
abstract algorithms arxiv complexities complexity coverage cs.it cs.lg cs.sy data distribution eess.sy exploration math.it math.st offline paper prior reinforcement reinforcement learning sample shift stat.ml stat.th type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote