90 citations · 167 across the 15 of their papers we have counts for
17 papers
The Benefits of Power Regularization in Cooperative Reinforcement Learning
Michelle Li, Michael Dennis
Cooperative Multi-Agent Reinforcement Learning (MARL) algorithms, trained only to optimize task reward, can lead to a concentration of power where the failure or adversarial intent…
Stabilizing Unsupervised Environment Design with a Learned Adversary
Ishita Mediratta, Minqi Jiang, Jack Parker-Holder +3
A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations. This challenge m…
Who Needs to Know? Minimal Knowledge for Optimal Coordination
Niklas Lauffer, Ameesh Shah, Micah Carroll +2
To optimally coordinate with others in cooperative games, it is often crucial to have information about one's collaborators: successful driving requires understanding which side of…
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Mikayel Samvelyan, Akbir Khan, Michael Dennis +5
Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning a…
Adversarial Policies Beat Superhuman Go AIs
Tony T. Wang, Adam Gleave, Tom Tseng +8
We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our…
Cooperative and uncooperative institution designs: Surprises and problems in open-source game theory
Andrew Critch, Michael Dennis, Stuart Russell
It is increasingly possible for real-world agents, such as software-based agents or human institutions, to view the internal programming of other such agents that they interact wit…