Maintaining Cooperation in Noisy Environments

To prevent or alleviate conflicts in multi-agent environments, it is important to distinguish between situations where another agent has misbehaved intentionally and situations where the misbehavior was accidental. One situation where this problem arises is the Noisy Iterated Prisoner's Dilemma, a version of the Iterated Prisoner's Dilemma (IPD) in which there is a nonzero probability that a "cooperate" action will accidentally be changed into a "defect" action and vice versa. Tit-For-Tat and other strategies that do quite well in the ordinary (non-noisy) IPD can do quite badly in the Noisy IPD. This paper presents a technique called symbolic noise detection, for detecting whether anomalies in player's behavior are deliberate or accidental. This idea to use player's deterministic behavior to tell whether an action has been affected by noise. We also present DBS, an algorithm that uses symbolic noise detection in the Noisy IPD. DBS constructs a m...

• Type: Conference
• Year: 2006
• Where: AAAI
• Authors: Tsz-Chiu Au, Dana S. Nau
• Keywords: AAAI 2006, Intelligent Agents, Iterated Prisoner Dilemma, Prisoner's Dilemma, Symbolic Noise Detection