Aristotle University of Thessaloniki
University of Edinburgh
UCL
Misha LaskinCo-founder and CEO · Reflection AIResearcher↗
Researcher · Founder · Executive
Ioannis Antonoglou
Reflection AICo-founder, President and CTO
Antonoglou contributed to the deep Q-network that learned Atari games from pixels[1], then to AlphaGo, AlphaZero, and MuZero[2]. Across these systems, he helped show that one neural architecture could learn perception, planning, and strategy from experience rather than relying mainly on hand-written rules.
Career & education
Current roleReflection AI2024-presentCo-founder, President and CTO
Reflection AI2024-presentPreviously
Google DeepMind2012-2024Senior Staff Research Scientist
Google DeepMind2012-2024Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations147,779As of Nov 1, '26
citations+2,700Since last snapshot, Oct 1, '26
Selected contributions
Human-level control through deep reinforcement learning
With Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves and others ·Presented DQN, learning to play 49 Atari games from screen images and game scores.
Mastering the game of Go with deep neural networks and tree search
With David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser and others ·AlphaGo combined neural networks and search to beat a professional Go player.
Playing Atari with Deep Reinforcement Learning
With Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Daan Wierstra and Martin RiedmillerShowed a neural network could learn Atari games directly from screen pixels and rewards.
References
- Human-Level Control through Deep Reinforcement Learningpubmed.ncbi.nlm.nih.gov
The team describes a system that learned to play Atari games from screen pixels and game scores.
- Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelarxiv.org
The MuZero paper describes how the system learns what it needs to plan without being given the game's rules.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 7, 2026 · Checked for accuracy and new information.
