We examine recent claims that a particular Q-learning algorithm used by
competitorsautonomously'and systematically learns to collude, resulting in supracompetitive …

We present two new findings based on annual antipsychotic US prescribing data from IMS
Health on 2867 psychiatrists who wrote 50 or more prescriptions in 2007. First, many of …

As autonomous agents proliferate in the real world, both in software and robotic settings,
they will increasingly need to band together for cooperative activities with previously …

We study a class of symmetric strategic experimentation games. Each of two players faces
an (exponential) two-armed bandit problem, and must decide when to stop experimenting …

We consider a model of persuasion in which an agent who tries to persuade a decision
maker can sequentially acquire imperfect signals. The agent's information acquisition is …

We consider the setting of repeated fair division between two players, denoted Alice and
Bob, with private valuations over a cake. In each round, a new cake arrives, which is …

Repeated games with unknown payoff distributions are analogous to a single decision
maker's “multi‐armed bandit” problem. Each state of the world corresponds to a different …

The stochastic multi-armed bandit model captures the tradeoff between exploration and
exploitation. We study the effects of competition and cooperation on this tradeoff. Suppose …

Before deployment, agents designed for multiagent team settings are commonly developed
together or are given standardized communication and coordination protocols. However, in …

Robots are becoming cheaper and more durable as manufacturing processes improve, and
they are becoming useful for an increasing number of tasks as artificial intelligence …