Asynchronous Methods for Deep Reinforcement Learning
Volodymyr Mnih and collaborators submitted 'Asynchronous Methods for Deep Reinforcement Learning' on February 4, 2016. The paper presents asynchronous variants of four reinforcement-learning algorithms and reports that its asynchronous actor-critic variant was the best-performing method in the study.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented deep-reinforcement-learning research milestone for asynchronous parallel actor-learners and the asynchronous actor-critic method commonly associated with A3C.
People, organizations & technologies
PEOPLE
Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu
TECHNOLOGIES
Asynchronous Advantage Actor-Critic (A3C), Deep reinforcement learning, Actor-critic
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-14T19:05:28+08:00
The original arXiv record establishes the February 4 2016 submission date, title, authors, and the paper's asynchronous deep-reinforcement-learning framework. The ICML 2016 PMLR proceedings independently establish the paper's conference publication and describe the asynchronous actor-critic variant as the best-performing method reported in the paper. No invention date, development start, development geography, institutional affiliation, ancestry, influence, causality, universal-priority claim, or relationship is inferred.
Sources
Asynchronous Methods for Deep Reinforcement Learning
arXiv
PUBLISHED
2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Proceedings of Machine Learning Research
Trace the chronology
Record identity
LINEAiGE IDa3c-asynchronous-methods-2016