research
∙
05/29/2023
Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity
Is it possible to evaluate the moral cognition of complex artificial age...
share
research
∙
05/01/2023
Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
In social psychology, Social Value Orientation (SVO) describes an indivi...
research
∙
11/24/2022
Melting Pot 2.0
Multi-agent artificial intelligence research promises a path to develop ...
research
∙
01/05/2022
Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria
A key challenge in the study of multiagent cooperation is the need for i...
research
∙
10/21/2021
Statistical discrimination in learning agents
Undesired bias afflicts both human and algorithmic decision making, and ...
research
∙
11/13/2020
DeepMind Lab2D
We present DeepMind Lab2D, a scalable environment simulator for artifici...
research
∙
10/18/2020
Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences
Game theoretic views of convention generally rest on notions of common k...
research
∙
10/01/2020
D3C: Reducing the Price of Anarchy in Multi-Agent Learning
Even in simple multi-agent systems, fixed incentives can lead to outcome...
research
∙
02/06/2020
Social Diversity and Social Preferences in Mixed-Motive Reinforcement Learning
Recent research on reinforcement learning in pure-conflict and pure-comm...
research
∙
11/14/2018
Evolving intrinsic motivations for altruistic behavior
Multi-agent cooperation is an important feature of the natural world. Ma...
research
∙
03/23/2018
Inequity aversion improves cooperation in intertemporal social dilemmas
Groups of humans are often able to find ways to cooperate with one anoth...
research
∙
03/23/2018