Social Reward Shaping in the Prisoner's Dilemma


Babes, Monica, Munoz de Cote, Enrique and Littman, Michael L. (2008) Social Reward Shaping in the Prisoner's Dilemma. At Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS)

Download

[img] PDF - Published Version
Download (113Kb)

Description/Abstract

Reward shaping is a well-known technique applied to help reinforcement-learning agents converge more quickly to near-optimal behavior. In this paper, we introduce \emph{social reward shaping}, which is reward shaping applied in the multiagent-learning framework. We present preliminary experiments in the iterated Prisoner's dilemma setting that show that agents using social reward shaping appropriately can behave more effectively than other classical learning and non-learning strategies. In particular, we show that these agents can both lead ---encourage adaptive opponents to stably cooperate--- and follow ---adopt a best-response strategy when paired with a fixed opponent--- where better known approaches achieve only one of these objectives.

Item Type: Conference or Workshop Item (Poster)
Keywords: Reinforcement Learning, leader/follower strategies, iterated prisoner's dilemma, game theory, subgame perfect equilibrium
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 266919
Date Deposited: 17 Nov 2008 14:36
Last Modified: 27 Mar 2014 20:12
Contact Email Address: jemc@ecs.soton.ac.uk
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/266919

Actions (login required)

View Item View Item