The decision-making process of computer-controlled opponents in video games is called game AI. Adaptive game AI can improve the entertainment value of games by allowing computer-controlled opponents to fix weaknesses automatically in the game AI, and to respond to changes in human-player tactics. Dynamic scripting is a reinforcement learning approach to adaptive game AI that learns, during game...

Agent modelling is a challenging problem in many modern artificial intelligence applications. The agent modelling task is especially difficult when handling stochastic choices, deliberately hidden information, dynamic agents, and the need for fast learning. State estimation techniques, such as Kalman filtering and particle filtering, have addressed many of these challenges, but have received li...

The paper presents an analysis of the policy advocacy strategies used by both proponents and opponents of needle exchange programs in the US, drawing on the analytic framework developed by Stone. Based on a case study of the politics of needle exchange in Massachusetts, we argue that proponents of needle exchange have relied almost exclusively on empirical scientific arguments to build their ca...

Poker provides a challenging domain for Artificial Intelligence research due to the game’s properties such as hidden information (the other player’s cards) and nondeterminism (random shuffling of the deck). Recent approaches to Poker research have required intensive knowledge engineering efforts. This thesis discusses the design and development of a CASe-based Poker playER (CASPER) that uses th...

A sophisticated player is an individual who takes the action of the opponents, in a strategic situation, as determined by decision of rational opponents, and acts accordingly. A sophisticated agent is rational in the choice of his action, but ignores the fact that he is part of a strategic situation. We discuss a notion of equilibrium with sophisticated agents, we provide conditions for its exi...

Levels of inter-male aggression, both in laboratory encounters and in the field, rise dramatically during the breeding season, closely paralleling the seasonal rise in testosterone. However, post-pubertally castrated males also show the dramatic seasonal rise in aggression in laboratory encounters with castrated opponents and show no decrement in fighting ability when paired with intact opponen...

An approach to auctions and bidding is founded on observations and expectations of the opponents' behavior and not on assumptions concerning the opponents' motivations or internal reasoning. The approach draws ideas from information theory. A bidding agent employs maximum entropy inference to determine its actions on the basis of this uncertain data. Maximum entropy inference may be applied bot...

Multiplayer games are becoming large part of today’s digital entertainment. As more game players gain access to high-speed internet connections multiplayer games can grow becoming more ambitious than ever before. Multiplayer games can provide a much richer experience than single player games. Human opponents can be much more challenging than artificial opponents. They learn and adapt and can be...

We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against t...