Sciweavers

ATAL
2010
Springer
13 years 8 months ago
Success, strategy and skill: an experimental study
In many AI settings an agent is comprised of both actionplanning and action-execution components. We examine the relationship between the precision of the execution component, the...
Christopher Archibald, Alon Altman, Yoav Shoham
ATAL
2010
Springer
13 years 8 months ago
High-level reinforcement learning in strategy games
Video games provide a rich testbed for artificial intelligence methods. In particular, creating automated opponents that perform well in strategy games is a difficult task. For in...
Christopher Amato, Guy Shani
ATAL
2010
Springer
13 years 8 months ago
Using counterfactual regret minimization to create competitive multiplayer poker agents
Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers)....
Nicholas Abou Risk, Duane Szafron
ATAL
2010
Springer
13 years 8 months ago
Self-organization for coordinating decentralized reinforcement learning
Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous ...
Chongjie Zhang, Victor R. Lesser, Sherief Abdallah
ATAL
2010
Springer
13 years 8 months ago
Reasoning about strategies of multi-agent programs
Verification of multi-agent programs is a key problem in agent research and development. This paper focuses on multi-agent programs that consist of a finite set of BDI-based agent...
Mehdi Dastani, Wojciech Jamroga
ATAL
2010
Springer
13 years 8 months ago
Cultivating desired behaviour: policy teaching via environment-dynamics tweaks
In this paper we study, for the first time explicitly, the implications of endowing an interested party (i.e. a teacher) with the ability to modify the underlying dynamics of the ...
Zinovi Rabinovich, Lachlan Dufton, Kate Larson, Ni...
ATAL
2010
Springer
13 years 8 months ago
Changing neighbours: improving tag-based cooperation
In systems of autonomous self-interested agents, in which agents' neighbourhoods are defined by their connections to others, cooperation can arise through observation of the ...
Nathan Griffiths, Michael Luck
ATAL
2010
Springer
13 years 8 months ago
Using graph analysis to study networks of adaptive agent
Experimental analysis of networks of cooperative learning agents (to verify certain properties such as the system's stability) has been commonly used due to the complexity of...
Sherief Abdallah
ATAL
2010
Springer
13 years 8 months ago
Independent navigation of multiple robots and virtual agents
We demonstrate an approach for collision- and oscillationfree navigation of multiple robots or virtual agents amongst each other. Each entity acts independently and uses only both...
Jamie Snape, Stephen J. Guy, Jur P. van den Berg
ATAL
2010
Springer
13 years 8 months ago
Aggregation-mediated collective perception and action in a group of miniature robots
We introduce a novel case study in which a group of miniaturized robots screen an environment for undesirable agents, and destroy them. Because miniaturized robots are usually end...
Grégory Mermoud, Loïc Matthey, William...