Volodymyr Mnih
Research scientist at Google DeepMind; first author of the deep Q-network (DQN) and A3C papers
- Research scientist, Google DeepMind1
Volodymyr (Vlad) Mnih is a research scientist at Google DeepMind, according to Mnih's homepage, which lists publications on deep reinforcement learning and visual attention. Mnih is first author of "Playing Atari with Deep Reinforcement Learning" (2013), which trained a convolutional network with a variant of Q-learning to play Atari 2600 games from raw pixels, and of the Nature paper "Human-level Control through Deep Reinforcement Learning". Mnih is also first author of "Asynchronous Methods for Deep Reinforcement Learning" (2016), which introduced asynchronous actor-learner variants of standard reinforcement learning algorithms.123
Work
Deep Q-network (DQN) (external site: arxiv.org)Published research
First author of the 2013 paper "Playing Atari with Deep Reinforcement Learning" and of the 2015 Nature paper "Human-level Control through Deep Reinforcement Learning", for which the homepage links code.21
Asynchronous Methods for Deep Reinforcement Learning (A3C) (external site: arxiv.org)Published research
First author of the 2016 paper presenting asynchronous variants of four reinforcement learning algorithms trained with parallel actor-learners.3
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.