Michael Dennis
Michael Dennis
Google DeepMind
Verified email at - Homepage
Cited by
Cited by
Adversarial policies: Attacking deep reinforcement learning
A Gleave, M Dennis, C Wild, N Kant, S Levine, S Russell
(ICLR 2020) - Eighth International Conference on Learning Representations, 2020
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
M Dennis, N Jaques, E Vinitsky, A Bayen, S Russell, A Critch, S Levine
(NeurIPS 2020) - Advances in Neural Information Processing Systems 33, 2020
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
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
Quantifying Differences in Reward Functions
A Gleave, M Dennis, S Legg, S Russell, J Leike
(ICLR 2021) - Ninth International Conference on Learning Representations, 2021
Adversarial Policies Beat Professional-Level Go AIs
TT Wang, A Gleave, N Belrose, T Tseng, J Miller, MD Dennis, Y Duan, ...
arXiv preprint arXiv:2211.00241, 2022
A new formalism, method and open issues for zero-shot coordination
J Treutlein, M Dennis, C Oesterheld, J Foerster
International Conference on Machine Learning, 10413-10423, 2021
Benefits of Assistance over Reward Learning
R Shah, P Freire, N Alex, R Freedman, D Krasheninnikov, L Chan, ...
Genie: Generative Interactive Environments
J Bruce, M Dennis, A Edwards, J Parker-Holder, Y Shi, E Hughes, M Lai, ...
arXiv preprint arXiv:2402.15391, 2024
MAESTRO: Open-ended environment design for multi-agent reinforcement learning
M Samvelyan, A Khan, M Dennis, M Jiang, J Parker-Holder, J Foerster, ...
arXiv preprint arXiv:2303.03376, 2023
Grounding Aleatoric Uncertainty in Unsupervised Environment Design
M Jiang, M Dennis, J Parker-Holder, A Lupu, H Küttler, E Grefenstette, ...
arXiv preprint arXiv:2207.05219, 2022
Cooperative and uncooperative institution designs: Surprises and problems in open-source game theory
A Critch, M Dennis, S Russell
arXiv preprint arXiv:2208.07006, 2022
The Stretch Factor of Hexagon-Delaunay Triangulations
L Perkovic, M Dennis, DT Türkoğlu
Journal of Computational Geometry 12 (2), 86–125-86–125, 2021
Stabilizing unsupervised environment design with a learned adversary
I Mediratta, M Jiang, J Parker-Holder, M Dennis, E Vinitsky, T Rocktäschel
Conference on Lifelong Learning Agents, 270-291, 2023
minimax: Efficient Baselines for Autocurricula in JAX
M Jiang, M Dennis, E Grefenstette, T Rocktäschel
arXiv preprint arXiv:2311.12716, 2023
Improving Social Welfare While Preserving Autonomy via a Pareto Mediator
S McAleer, J Lanier, M Dennis, P Baldi, R Fox
arXiv preprint arXiv:2106.03927, 2021
Accumulating Risk Capital Through Investing in Cooperation
C Roman, M Dennis, A Critch, S Russell
(AAMAS 2021) - 20th International Conference on Autonomous Agents and …, 2021
Who Needs to Know? Minimal Knowledge for Optimal Coordination
N Lauffer, A Shah, M Carroll, MD Dennis, S Russell
International Conference on Machine Learning, 18599-18613, 2023
Refining Minimax Regret for Unsupervised Environment Design
M Beukman, S Coward, M Matthews, M Fellows, M Jiang, M Dennis, ...
arXiv preprint arXiv:2402.12284, 2024
The Benefits of Power Regularization in Cooperative Reinforcement Learning
M Li, M Dennis
Proceedings of the 2023 International Conference on Autonomous Agents and …, 2023
The system can't perform the operation now. Try again later.
Articles 1–20