| Genie: Generative Interactive Environments J Bruce, M Dennis, A Edwards, J Parker-Holder, Y Shi, E Hughes, M Lai, ... ICML 2024 (Best Paper Award), 2024 | 438 | 2024 |
| Effective diversity in population based reinforcement learning J Parker-Holder, A Pacchiano, KM Choromanski, SJ Roberts Advances in Neural Information Processing Systems 33, 18050-18062, 2020 | 213 | 2020 |
| Human-timescale adaptation in an open-ended task space AA Team, J Bauer, K Baumli, S Baveja, F Behbahani, A Bhoopchand, ... ICML 2023 (Oral), 2023 | 202* | 2023 |
| Evolving curricula with regret-based environment design J Parker-Holder, M Jiang, M Dennis, M Samvelyan, J Foerster, ... International Conference on Machine Learning, 17473-17498, 2022 | 199 | 2022 |
| Automated reinforcement learning (autorl): A survey and open problems J Parker-Holder, R Rajan, X Song, A Biedenkapp, Y Miao, T Eimer, ... Journal of Artificial Intelligence Research 74, 517-568, 2022 | 168 | 2022 |
| Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts M Samvelyan, SC Raparthy, A Lupu, E Hambro, AH Markosyan, M Bhatt, ... NeurIPS 2024, 2024 | 166* | 2024 |
| Replay-guided adversarial environment design M Jiang, M Dennis, J Parker-Holder, J Foerster, E Grefenstette, ... Advances in Neural Information Processing Systems 34, 1884-1897, 2021 | 154 | 2021 |
| Synthetic Experience Replay C Lu, PJ Ball, YW Teh, J Parker-Holder NeurIPS 2023, 2023 | 139 | 2023 |
| Minihack the planet: A sandbox for open-ended reinforcement learning research M Samvelyan, R Kirk, V Kurin, J Parker-Holder, M Jiang, E Hambro, ... arXiv preprint arXiv:2109.13202, 2021 | 136 | 2021 |
| Provably efficient online hyperparameter optimization with population-based bandits J Parker-Holder, V Nguyen, SJ Roberts Advances in neural information processing systems 33, 17200-17211, 2020 | 103 | 2020 |
| Revisiting Design Choices in Offline Model-Based Reinforcement Learning C Lu, PJ Ball, J Parker-Holder, MA Osborne, SJ Roberts arXiv preprint arXiv:2110.04135, 2021 | 89* | 2021 |
| Open-Endedness is Essential for Artificial Superhuman Intelligence E Hughes, M Dennis, J Parker-Holder, F Behbahani, A Mavalankar, Y Shi, ... ICML 2024 (Oral), 2024 | 86 | 2024 |
| Tactical optimism and pessimism for deep reinforcement learning T Moskovitz, J Parker-Holder, A Pacchiano, M Arbel, M Jordan Advances in Neural Information Processing Systems 34, 12849-12863, 2021 | 83 | 2021 |
| BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games D Paglieri, B Cupiał, S Coward, U Piterbarg, M Wolczyk, A Khan, ... ICLR 2025, 2025 | 81* | 2025 |
| Video as the New Language for Real-World Decision Making S Yang, J Walker, J Parker-Holder, Y Du, J Bruce, A Barreto, P Abbeel, ... ICML 2024, 2024 | 77* | 2024 |
| Same state, different task: Continual reinforcement learning without interference S Kessler, J Parker-Holder, P Ball, S Zohren, SJ Roberts Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7143-7151, 2022 | 76* | 2022 |
| Genie 2: A Large-Scale Foundation World Model J Parker-Holder, P Ball, J Bruce, V Dasagi, K Holsheimer, C Kaplanis, ... https://deepmind.google/discover/blog/genie-2-a-large-scale-foundation-world …, 2024 | 75* | 2024 |
| Challenges and opportunities in offline reinforcement learning from visual observations C Lu, PJ Ball, TGJ Rudner, J Parker-Holder, MA Osborne, YW Teh arXiv preprint arXiv:2206.04779, 2022 | 71 | 2022 |
| Augmented world models facilitate zero-shot dynamics generalization from a single offline environment PJ Ball, C Lu, J Parker-Holder, S Roberts International Conference on Machine Learning, 619-629, 2021 | 70 | 2021 |
| From complexity to simplicity: Adaptive es-active subspaces for blackbox optimization KM Choromanski, A Pacchiano, J Parker-Holder, Y Tang, V Sindhwani Advances in Neural Information Processing Systems 32, 2019 | 63 | 2019 |
Tim RocktäschelGoogle DeepMind, Professor of AI at UCL, Fellow ELLISVerified email at cs.ucl.ac.uk
