Sotabase

Career

· Honorary Lecturer at UCL, UCL DARK Lab2023–

Publications (66)

Genie: Generative Interactive Environments
International Conference on Machine Learning · 2024
377
cited
Effective Diversity in Population-Based Reinforcement Learning
Neural Information Processing Systems · 2020
180
cited
Evolving Curricula with Regret-Based Environment Design
International Conference on Machine Learning · 2022
166
cited
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Neural Information Processing Systems · 2024
158
cited
Human-Timescale Adaptation in an Open-Ended Task Space
International Conference on Machine Learning · 2023
149
cited
Replay-Guided Adversarial Environment Design
Neural Information Processing Systems · 2021
130
cited
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Journal of Artificial Intelligence Research · 2022
128
cited
Synthetic Experience Replay
Neural Information Processing Systems · 2023
111
cited
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
NeurIPS Datasets and Benchmarks · 2021
105
cited
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
Neural Information Processing Systems · 2020
97
cited
Video as the New Language for Real-World Decision Making
International Conference on Machine Learning · 2024
84
cited
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
International Conference on Learning Representations · 2024
72
cited
Tactical Optimism and Pessimism for Deep Reinforcement Learning
Neural Information Processing Systems · 2021
70
cited
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Trans. Mach. Learn. Res. · 2022
63
cited
Revisiting Design Choices in Offline Model Based Reinforcement Learning
International Conference on Learning Representations · 2021
60
cited
Open-Endedness is Essential for Artificial Superhuman Intelligence
International Conference on Machine Learning · 2024
58
cited
Same State, Different Task: Continual Reinforcement Learning without Interference
AAAI Conference on Artificial Intelligence · 2021
55
cited
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
International Conference on Machine Learning · 2021
54
cited
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization
Neural Information Processing Systems · 2019
52
cited
Ready Policy One: World Building Through Active Learning
International Conference on Machine Learning · 2020
52
cited
Sotabase