Roy Fox
Biography
Roy Fox, Ph.D., is Assistant Professor in the Department of Computer Science at the University of California, Irvine. His research focuses on reinforcement learning and control, with particular emphasis on information-theoretic methods, hierarchical learning, and applications to robotics and multi-agent systems. Fox has developed methods for learning control programs from demonstrations, population-based approaches for multi-agent reinforcement learning, and techniques for safe reinforcement learning through formal verification.
Fox received his Ph.D. from the School of Computer Science and Engineering at Hebrew University in 2017, where he developed information-theoretic methods for planning and learning in partially observable Markov decision processes under the supervision of Naftali Tishby. He completed a postdoctoral position at the University of California, Berkeley from 2016 to 2019, working with Ion Stoica and Ken Goldberg, where he contributed to the development of RLlib, a widely-used distributed reinforcement learning library. During his doctoral studies, Fox spent a year as an exchange student at the Center for Theoretical Neuroscience at Columbia University.
Fox's research has been supported by grants from the National Science Foundation, DARPA, and the Binational Science Foundation. He has served as co-organizer for workshops on hierarchical reinforcement learning and probabilistic reinforcement learning at NeurIPS, and has been a senior program committee member for conferences including ICLR, NeurIPS, and IJCAI. He received the Chancellor's Award for Excellence in Undergraduate Research from UCI in 2022.
Return to topEducation
- PhD in Computer Science, Hebrew University, 2017
- MS in Computer Science, Technion, 2008
- BS in Computer Science, Hebrew University, 2001
- BS in Medical Sciences, Hebrew University Hadassah Medical School, 2000
Areas of Expertise
- Reinforcement Learning
- Hierarchical Control Programs
- Multi-Agent Game Theory
- Information-Theoretic Planning
- Vision-Language World Models
- Safe Robot Learning
- Neural Program Synthesis
Recent Publications
- Kyungmin Kim, John Lanier, Roy Fox, “Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions”, 2025. Presented at 2nd Reinforcement Learning Conference (RLC 2025).
- Zhuojun Ying, Frederick Callaway, Roy Fox, Anastasia Kiyonaga, Marcelo Mattar, “A Variational Neural Network Model of Resource-Rational Reward Encoding in Human Planning”, 2025. Presented at 47th Annual Meeting of the Cognitive Science Society (CogSci 2025).
- Kyungmin Kim, Davide Corsi, Andoni Rodríguez, John Lanier, Benjami Parellada, Pierre Baldi, César Sánchez, Roy Fox, “Realizable Continuous-Space Shields for Safe Reinforcement Learning”, 2025. Presented at 7th Annual Learning for Dynamics and Control Conference (L4DC 2025).
- Davide Corsi, Guy Amir, Andoni Rodríguez, Guy Katz, César Sánchez, Roy Fox, “Verification-Guided Shielding for Deep Reinforcement Learning”, 2024. Presented at 1st Reinforcement Learning Conference (RLC 2024).
- Armin Karamzade, Kyungmin Kim, Montek Kalsi, Roy Fox, “Reinforcement Learning from Delayed Observations via World Models”, 2024. Presented at 1st Reinforcement Learning Conference (RLC 2024).
- Kolby Nottingham, Bodhisattwa Majumder, Bhavana Dalvi, Sameer Singh, Peter Clark, Roy Fox, “Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills”, 2024. Presented at 41st International Conference on Machine Learning (ICML 2024).
- Stephen McAleer, John Lanier, Kevin Wang, Pierre Baldi, Tuomas Sandholm, Roy Fox, “Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games”, 2024. Presented at 12th International Conference on Learning Representations (ICLR 2024).
- Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi, Hannaneh Hajishirzi, Sameer Singh, Roy Fox, “Do Embodied Agents Dream of Pixelated Sheep?: Embodied Decision Making using Language Guided World Modelling”, 2023. Presented at 40th International Conference on Machine Learning (ICML 2023).
- Dmitrii Krylov, Pooya Khajeh, Junhan Ouyang, Thomas Reeves, Tongkai Liu, Hiba Ajmal, Hamidreza Aghasi, Roy Fox, “Learning to Design Analog Circuits to Meet Threshold Specifications”, 2023. Presented at 40th International Conference on Machine Learning (ICML 2023).
- Litian Liang, Yaosheng Xu, Stephen McAleer, Dailin Hu, Alexander Ihler, Pieter Abbeel, Roy Fox, “Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks”, 2022. Presented at 39th International Conference on Machine Learning (ICML 2022).
- Roy Fox, Stephen McAleer, Will Overman, Ioannis Panageas, “Independent Natural Policy Gradient Always Converges in Markov Potential Games”, 2022. Presented at 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022).
- John Lanier, Stephen McAleer, Pierre Baldi, Roy Fox, “Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments”, 2022. Presented at Deep Reinforcement Learning workshop (DeepRL @ NeurIPS 2022).
- Kolby Nottingham, Alekhya Pyla, Sameer Singh, Roy Fox, “Learning to Query Internet Text for Informing Reinforcement Learning Agents”, 2022. Presented at 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022).
- Stephen McAleer, John Lanier, Kevin Wang, Pierre Baldi, Roy Fox, “Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games”, 2021. Presented at 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
This profile was created with the help of AI.
Last updated on 3/24/2026.