all AI news
Mildly Conservative Q-Learning for Offline Reinforcement Learning
Feb. 22, 2024, 5:42 a.m. | Jiafei Lyu, Xiaoteng Ma, Xiu Li, Zongqing Lu
cs.LG updates on arXiv.org arxiv.org
Abstract: Offline reinforcement learning (RL) defines the task of learning from a static logged dataset without continually interacting with the environment. The distribution shift between the learned policy and the behavior policy makes it necessary for the value function to stay conservative such that out-of-distribution (OOD) actions will not be severely overestimated. However, existing approaches, penalizing the unseen actions or regularizing with the behavior policy, are too pessimistic, which suppresses the generalization of the value function …
arxiv cs.ai cs.lg offline q-learning reinforcement reinforcement learning type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Machine Learning Engineer
@ Samsara | Canada - Remote