AAAI
2006
14 years 2 months ago
2006
To prevent or alleviate conflicts in multi-agent environments, it is important to distinguish between situations where another agent has misbehaved intentionally and situations wh...
ATAL
2008
Springer
14 years 2 months ago
2008
Springer
Reward shaping is a well-known technique applied to help reinforcement-learning agents converge more quickly to nearoptimal behavior. In this paper, we introduce social reward sha...
ECAI
2006
Springer
14 years 4 months ago
2006
Springer
Abstract. Computational Game Theory is a way to study and evaluate behaviors using game theory models, via agent-based computer simulations. One of the most known example of this a...
ATAL
2006
Springer
14 years 4 months ago
2006
Springer
In many Multi-Agent Systems (MAS), agents (even if selfinterested) need to cooperate in order to maximize their own utilities. Most of the multi-agent learning algorithms focus on...
ATAL
2006
Springer
14 years 4 months ago
2006
Springer
This paper focuses on the Noisy Iterated Prisoner's Dilemma, a version of the Iterated Prisoner's Dilemma (IPD) in which there is a nonzero probability that a "coop...
ACSC
2004
IEEE
14 years 4 months ago
2004
IEEE
Table 1 shows the payoff to player one. The same matrix also holds for player two. Player one can gain the maximum 5 points (T = 5) by defection if player two cooperates. However,...
EPS
1998
Springer
14 years 4 months ago
1998
Springer
The Classical Iterated Prisoner's Dilemma (CIPD) is used to study the evolution of cooperation. We show, with a genetic approach, how basic ideas could be used in order to gen...
EPS
1998
Springer
14 years 4 months ago
1998
Springer
We investigate the following question. Do populations of evolving agents adapt only to their recent environment or do general adaptive features appear over time? We find statistica...
GECCO
2005
Springer
14 years 6 months ago
2005
Springer
The iterated prisoner’s dilemma is a widely used computational model of cooperation and conflict. Many studies report emergent cooperation in populations of agents trained to p...
ATAL
2005
Springer
14 years 6 months ago
2005
Springer
In multi-agent communities, trust is required when agents hold different beliefs or conflicting goals. We present a framework for decomposing agent reputation into competence—...