Explainability techniques are crucial in gaining insights into the reaso...
Multiagent reinforcement learning (MARL) has benefited significantly fro...
The Game Theory Multi-Agent team at DeepMind studies several aspects...
In many multi-agent settings, participants can form teams to achieve
col...
Large graphs commonly appear in social networks, knowledge graphs,
recom...
Recent work has shown the potential benefit of selective prediction syst...
Undesired bias afflicts both human and algorithmic decision making, and ...
Nash equilibrium is a central concept in game theory. Several Nash solve...
Problems of cooperation–in which agents seek ways to jointly improve the...
When autonomous agents interact in the same environment, they must often...
Even in simple multi-agent systems, fixed incentives can lead to outcome...
Recent advances in deep reinforcement learning (RL) have led to consider...
Zero-sum games have long guided artificial intelligence research, since ...
Adversarial training, a special case of multi-objective optimization, is...
We study the problem of emergent communication, in which language arises...
Auctions are protocols to allocate goods to buyers who have preferences ...
Zero-sum games such as chess and poker are, abstractly, functions that
e...
We propose a new attention mechanism for neural based question answering...
All-pay auctions, a common mechanism for various human and agent
interac...
We study reinforcement learning of chatbots with recurrent neural networ...
We consider the task of predicting various traits of a person given an i...
We propose a new probabilistic graphical model that jointly models the
d...
Cooperative games model the allocation of profit from joint actions,
fol...
A key question in cooperative game theory is that of coalitional stabili...