Search

Fall 2014

Hawkin, John A

An agent in an adversarial, imperfect information environment must sometimes decide whether or not to take an action and, if they take the action, must choose a parameter value associated with that action. Examples include choosing to buy or sell some amount of resources or choosing whether or...

Fall 2020

Bhatt, Varun S.

Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication become necessary. Ideally, these agents should be trained in an incremental and decentralized manner. In...

Fall 2020

D'Orazio, Ryan

Computing a Nash equilibrium in zero-sum games, or more generally saddle point optimization, is a fundamental problem in game theory and machine learning, with applications spanning across a wide variety of domains, from generative modeling and computer vision to super-human AI in imperfect...

Spring 2016

Johanson, Michael Bradley

Games have been used as a testbed for artificial intelligence research since the earliest conceptions of computing itself. The twin goals of defeating human professional players at games, and of solving games outright by creating an optimal computer agent, have helped to drive practical ...

Spring 2016

Morrill, Dustin R

Game theoretic solution concepts, such as Nash equilibrium strategies that are optimal against worst case opponents, provide guidance in finding desirable autonomous agent behaviour. In particular, we wish to approximate solutions to complex, dynamic tasks, such as negotiation or bidding in...

Fall 2015

Davis, Trevor

Extensive-form games are a powerful framework for modeling sequential multi-agent interactions. In extensive-form games with imperfect information, Nash equilibria are generally used as a solution concept, but computing a Nash equilibrium can be intractable in large games. Instead, a variety of...