Gleave, Adam

Multi-Agent Risks from Advanced AI

Hammond, L., Chan, A., Clifton, J., Hoelscher-Obermaier, J., Khan, A., McLean, E., Smith, C., Barfuss, W., Foerster, J., Gavenčiak, T., et al. (2025) · arXiv

Ethics and Social Impacts of AIMulti-Agent Systems and Negotiation

Cited by 305

Adversarial Policies: Attacking Deep Reinforcement Learning

Gleave, A., Dennis, M., Wild, C., Kant, N., Levine, S., & Russell, S. (2019) · arXiv

Adversarial Robustness in Machine LearningReinforcement Learning in Robotics

Cited by 200

Adversarial Policies Beat Superhuman Go AIs

Wang, T. T., Gleave, A., Tseng, T., Pelrine, K., Belrose, N., Miller, J., Dennis, M. D., Duan, Y., Pogrebniak, V., Levine, S., et al. (2022) · arXiv

Adversarial Robustness in Machine LearningArtificial Intelligence in Games

Cited by 12

Understanding Learned Reward Functions

Michaud, E. J., Gleave, A., & Russell, S. (2020) · arXiv

Explainable Artificial Intelligence (XAI)Reinforcement Learning in Robotics

Cited by 7

Uncertainty Estimation for Language Reward Models

Gleave, A., & Irving, G. (2022) · arXiv

Machine Learning and AlgorithmsTopic Modeling

Cited by 6

Preprocessing Reward Functions for Interpretability

Jenner, E., & Gleave, A. (2022) · arXiv

Explainable Artificial Intelligence (XAI)Reinforcement Learning in Robotics

Cited by 2

On The Fragility of Learned Reward Functions

McKinney, L., Duan, Y., Krueger, D., & Gleave, A. (2023) · arXiv

Reinforcement Learning in RoboticsMachine Learning and Algorithms

Cited by 1