Publications
Ordered by citation count. Filter by domain or method.
- 1.A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Chen Tessler, Shahar Givony, Tom Zahavy, Daniel J Mankowitz, Shie Mannor · AAAI 2017
- 2.Graying the black box: Understanding DQNs
Tom Zahavy, Nir Ben Zrihem, Shie Mannor · ICML 2016
- 3.Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor · NeurIPS 2018
- 4.Deep learning reconstruction of ultrashort pulses
Tom Zahavy, Alex Dikopoltsev, Daniel Moss, Gil Ilan Haham, Oren Cohen, Shie Mannor, et al. · Optica 2018
- 5.Olympiad-level formal mathematical reasoning with reinforcement learning (AlphaProof)
Thomas Hubert, Rishi Mehta, Laurent Sartran, Miklós Z. Horváth, Tom Zahavy, et al. · Nature 2025
- 6.Reward is enough for convex MDPs
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh · NeurIPS 2021 (spotlight)
- 7.A Self-Tuning Actor-Critic Algorithm
Tom Zahavy, Zhongwen Xu, Vivek Veeriah, Matteo Hessel, Junhyuk Oh, Hado van Hasselt, David Silver, Satinder Singh · NeurIPS 2020
- 8.Is a picture worth a thousand words? A deep multi-modal architecture for product classification in e-commerce
Tom Zahavy, Abhinandan Krishnan, Alessandro Magnani, Shie Mannor · AAAI 2018
- 9.Bootstrapped Meta Learning
Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver, Satinder Singh · ICLR 2022 (Outstanding Paper Award)
- 10.Discovering Evolution Strategies via Meta-Black-Box Optimization
Robert Tjarko Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valenti Dallibard, Chris Lu, Satinder Singh, Sebastian Flennerhag · ICLR 2023
- 11.Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
Tom Zahavy, Yannick Schroecker, Feryal Behbahani, Kate Baumli, Sebastian Flennerhag, Shaobo Hou, Satinder Singh · ICLR 2023
- 12.Discovery of Options via Meta-Learned Subgoals
Vivek Veeriah, Tom Zahavy, Matteo Hessel, Zhongwen Xu, Junhyuk Oh, Iurii Kemaev, Hado van Hasselt, David Silver, Satinder Singh · NeurIPS 2021
- 13.Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Ofir Nabati, Tom Zahavy, Shie Mannor · ICML 2021
- 14.Shallow Updates for Deep Reinforcement Learning
Nir Levine, Tom Zahavy, Daniel J. Mankowitz, Aviv Tamar, Shie Mannor · NeurIPS 2017
- 15.Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Robert Tjarko Lange, Tom Schaul, Yutian Chen, Chris Lu, Tom Zahavy, Valentin Dallibard, Sebastian Flennerhag · GECCO 2023 (Best Paper Award nominee)
- 16.Online Apprenticeship Learning
Lior Shani, Tom Zahavy, Shie Mannor · AAAI 2021
- 17.Mastering board games by external and internal planning with language models
John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Tom Zahavy, et al. · ICML 2025
- 18.Inverse Reinforcement Learning in Contextual MDPs
Stav Belogolovsky, Philip Korsunsky, Shie Mannor, Chen Tessler, Tom Zahavy · Machine Learning Journal 2021 (Special Issue on RL for Real Life)
- 19.Diversifying AI: Towards Creative Chess with AlphaZero (AlphaZero db)
Tom Zahavy, Vivek Veeriah, Shaobo Hou, Kevin Waugh, Matthew Lai, Edouard Leurent, Nenad Tomašev, et al. · arXiv 2023
- 20.Ensemble robustness and generalization of stochastic deep learning algorithms
Tom Zahavy, Bingyi Kang, Alex Sivak, Jiashi Feng, Huan Xu, Shie Mannor · arXiv 2016
- 21.Discovering a set of policies for the worst case reward
Tom Zahavy, Andre Barreto, Daniel J Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh · ICLR 2021 (spotlight)
- 22.Deep learning reconstruction of ultrashort pulses from 2D spatial intensity patterns recorded by an all-in-line system in a single-shot
Ron Ziv, Alex Dikopoltsev, Tom Zahavy, Itay Rubinstein, Pavel Sidorenko, Oren Cohen, et al. · Optics Express 2020
- 23.Balancing Constraints and Rewards with Meta-Gradient D4PG
Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy Mann · ICLR 2021
- 24.ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy · ICML 2023
- 25.Discovering Diverse Nearly Optimal Policies with Successor Features
Tom Zahavy, Brendan O'Donoghue, Andre Barreto, Volodymyr Mnih, Sebastian Flennerhag, Satinder Singh
- 26.Systems, method, and non-transitory computer-readable storage media for multi-modal product classification
Alessandro Magnani, Tom Zahavy, Abhinandan Krishnan, Shie Mannor · US Patent 2019
- 27.Emphatic algorithms for deep reinforcement learning
Ray Jiang, Tom Zahavy, Zhongwen Xu, Adam White, Matteo Hessel, Charles Blundell, Hado van Hasselt · ICML 2021
- 28.Deep neural networks in single-shot ptychography
Oshri Wengrowicz, Or Peleg, Tom Zahavy, Barry Loevsky, Oren Cohen · Optics Express 2020
- 29.Action assembly: Sparse imitation learning for text-based games with combinatorial action spaces
Chen Tessler, Tom Zahavy, Deborah Cohen, Daniel J. Mankowitz, Shie Mannor · RLDM 2019
- 30.Apprenticeship Learning via Frank-Wolfe
Tom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour · AAAI 2020
- 31.Visualizing dynamics: from t-SNE to semi-MDPs
Nir Ben Zrihem, Tom Zahavy, Shie Mannor · ICML Workshop on Human Interpretability in ML 2016
- 32.Unknown mixing times in apprenticeship and reinforcement learning
Tom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour · UAI 2020
- 33.Meta Gradients in Non Stationary Environments
Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh · CoLLAs 2022 (Oral)
- 34.Train on validation: squeezing the data lemon
Guy Tennenholtz, Tom Zahavy, Shie Mannor · arXiv 2018
- 35.Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour · ALT 2020
- 36.PALM up: Playing in the Latent Manifold for Unsupervised Pretraining
Hao Liu, Tom Zahavy, Volodymyr Mnih, Satinder Singh · NeurIPS 2022
- 37.Sub-Nyquist sampling of OFDM signals for cognitive radios
Tom Zahavy, Oren Shayer, Deborah Cohen, Alexander Tolmachev, Yonina C. Eldar · ICASSP 2014
- 38.Optimistic Meta-Gradients
Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado van Hasselt, András György, Satinder Singh
- 39.Learning to Ask Medical Questions using Reinforcement Learning
Uri Shaham, Tom Zahavy, César Caraballo, Shiwani Mahajan, Daisy Massey, Harlan Krumholz · MLHC 2020
- 40.LLMs can't jump
Tom Zahavy · Position paper 2025
- 41.Methods and systems for constrained reinforcement learning
Ted Moskovitz, Brendan O'Donoghue, Tom Zahavy, Sebastian Flennerhag, et al. · US Patent 2024
- 42.POMRL: No-Regret Learning-to-Plan with Increasing Horizons
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy · TMLR 2023
- 43.Generating Creative Chess Puzzles (PuzzleGen)
Xifeng Feng, Vivek Veeriah, Mark Chiam, Michael Dennis, Federico Barbero, Johan Obando-Ceron, et al., Tom Zahavy · NeurIPS 2025
- 44.Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
Vivek Veeriah, Federico Barbero, Mark Chiam, Xifeng Feng, Michael Dennis, Ruchika Pachauri, Tim Tumiel, Tom Zahavy · arXiv 2025
- 45.Reinforcement learning by solution of a convex Markov decision process
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh · US Patent 2024
- 46.Acceleration in Policy Optimization
Veronica Chelu, Tom Zahavy, Arthur Guez, Doina Precup, Sebastian Flennerhag · arXiv 2023
- 47.Improving techniques for diagnostics of laser pulses by compact representations
Pavel Sidorenko, Alex Dikopoltsev, Tom Zahavy, Oren Lahav, Sivan Gazit, Yoav Shechtman, et al. · Optics Express 2019
- 48.COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Tom Zahavy, Shaobo Hou, Tim Tumiel, James Doran, Francesco Faccio, Xifeng Feng, Alex Havrilla, Iurii Khytryi, et al. · arXiv 2026
- 49.Meta-learned evolutionary strategies optimizer
Robert Tjarko Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valentin Dalibard, Chris Lu, et al. · US Patent 2024
- 50.Neural network reinforcement learning with diverse policies
Tom Zahavy, Brendan O'Donoghue, André Barreto, Sebastian Flennerhag, Volodymyr Mnih, et al. · US Patent 2024
- 51.Learning options for action selection with meta-gradients in multi-task reinforcement learning
Vivek Veeriah, Tom Zahavy, Matteo Hessel, et al. · US Patent 2023
- 52.APART: Diverse Skill Discovery using All Pairs with Ascending Reward and DropouT
Hadar Schreiber, Tom Zahavy, Guillaume Desjardins, Alon Cohen · EWRL 2023
- 53.Deep Randomized Least Squares Value Iteration
Guy Adam, Tom Zahavy, Oron Anschel, Nahum Shimkin · 2020