all AI news
An Empirical Study of Implicit Regularization in Deep Offline RL. (arXiv:2207.02099v1 [cs.LG])
July 6, 2022, 1:10 a.m. | Caglar Gulcehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matt Hoffman, Razvan Pascanu, Arnaud Doucet
cs.LG updates on arXiv.org arxiv.org
Deep neural networks are the most commonly used function approximators in
offline Reinforcement Learning these days. Prior works have shown that neural
nets trained with TD-learning and gradient descent can exhibit implicit
regularization that can be characterized by under-parameterization of these
networks. Specifically, the rank of the penultimate feature layer, also called
\textit{effective rank}, has been observed to drastically collapse during the
training. In turn, this collapse has been argued to reduce the model's ability
to further adapt in later …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
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