TY - CHAP
T1 - The Selfishness Level of Social Dilemmas
AU - Roesch, Stefan
AU - Leonardos, Stefanos
AU - Du, Yali
N1 - Publisher Copyright:
© 2024 International Foundation for Autonomous Agents and Multiagent Systems.
PY - 2024
Y1 - 2024
N2 - A key contributor to the success of modern societies is humanity's innate ability to meaningfully cooperate. Game-theoretic reasoning shows however, that an individual's amenity to cooperation is directly linked with the mechanics of the scenario at hand. Social dilemmas constitute a subset of such scenarios where players are caught in a dichotomy between the decision to cooperate, prioritising collective welfare, or defect, prioritising their own welfare. In this work, we study such games through the lens of 'the selfishness level', a standard game-theoretic metric which quantifies the extent to which a game's payoffs incentivize self-directed behaviours. Using this framework, we derive the conditions under which SDs can be resolved and, additionally, produce a first-step towards extending this metric to Markov games. Finally, we present an empirical analysis indicating the positive effects of selfishness-level-directed mechanisms in such environments.
AB - A key contributor to the success of modern societies is humanity's innate ability to meaningfully cooperate. Game-theoretic reasoning shows however, that an individual's amenity to cooperation is directly linked with the mechanics of the scenario at hand. Social dilemmas constitute a subset of such scenarios where players are caught in a dichotomy between the decision to cooperate, prioritising collective welfare, or defect, prioritising their own welfare. In this work, we study such games through the lens of 'the selfishness level', a standard game-theoretic metric which quantifies the extent to which a game's payoffs incentivize self-directed behaviours. Using this framework, we derive the conditions under which SDs can be resolved and, additionally, produce a first-step towards extending this metric to Markov games. Finally, we present an empirical analysis indicating the positive effects of selfishness-level-directed mechanisms in such environments.
KW - Game Theory
KW - Markov Game
KW - Multi-agent Reinforcement Learning
KW - Reinforcement Learning
KW - Social Dilemma
UR - http://www.scopus.com/inward/record.url?scp=85196390828&partnerID=8YFLogxK
M3 - Conference paper
AN - SCOPUS:85196390828
VL - 2024-May
T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
SP - 2441
EP - 2443
BT - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
T2 - 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024
Y2 - 6 May 2024 through 10 May 2024
ER -