{"title":"在具有间接互惠性的混合动机游戏中学习公平合作","authors":"Martin Smit, Fernando P. Santos","doi":"arxiv-2408.04549","DOIUrl":null,"url":null,"abstract":"Altruistic cooperation is costly yet socially desirable. As a result, agents\nstruggle to learn cooperative policies through independent reinforcement\nlearning (RL). Indirect reciprocity, where agents consider their interaction\npartner's reputation, has been shown to stabilise cooperation in homogeneous,\nidealised populations. However, more realistic settings are comprised of\nheterogeneous agents with different characteristics and group-based social\nidentities. We study cooperation when agents are stratified into two such\ngroups, and allow reputation updates and actions to depend on group\ninformation. We consider two modelling approaches: evolutionary game theory,\nwhere we comprehensively search for social norms (i.e., rules to assign\nreputations) leading to cooperation and fairness; and RL, where we consider how\nthe stochastic dynamics of policy learning affects the analytically identified\nequilibria. We observe that a defecting majority leads the minority group to\ndefect, but not the inverse. Moreover, changing the norms that judge in and\nout-group interactions can steer a system towards either fair or unfair\ncooperation. This is made clearer when moving beyond equilibrium analysis to\nindependent RL agents, where convergence to fair cooperation occurs with a\nnarrower set of norms. Our results highlight that, in heterogeneous populations\nwith reputations, carefully defining interaction norms is fundamental to tackle\nboth dilemmas of cooperation and of fairness.","PeriodicalId":501315,"journal":{"name":"arXiv - CS - Multiagent Systems","volume":"13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity\",\"authors\":\"Martin Smit, Fernando P. Santos\",\"doi\":\"arxiv-2408.04549\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Altruistic cooperation is costly yet socially desirable. As a result, agents\\nstruggle to learn cooperative policies through independent reinforcement\\nlearning (RL). Indirect reciprocity, where agents consider their interaction\\npartner's reputation, has been shown to stabilise cooperation in homogeneous,\\nidealised populations. However, more realistic settings are comprised of\\nheterogeneous agents with different characteristics and group-based social\\nidentities. We study cooperation when agents are stratified into two such\\ngroups, and allow reputation updates and actions to depend on group\\ninformation. We consider two modelling approaches: evolutionary game theory,\\nwhere we comprehensively search for social norms (i.e., rules to assign\\nreputations) leading to cooperation and fairness; and RL, where we consider how\\nthe stochastic dynamics of policy learning affects the analytically identified\\nequilibria. We observe that a defecting majority leads the minority group to\\ndefect, but not the inverse. Moreover, changing the norms that judge in and\\nout-group interactions can steer a system towards either fair or unfair\\ncooperation. This is made clearer when moving beyond equilibrium analysis to\\nindependent RL agents, where convergence to fair cooperation occurs with a\\nnarrower set of norms. Our results highlight that, in heterogeneous populations\\nwith reputations, carefully defining interaction norms is fundamental to tackle\\nboth dilemmas of cooperation and of fairness.\",\"PeriodicalId\":501315,\"journal\":{\"name\":\"arXiv - CS - Multiagent Systems\",\"volume\":\"13 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multiagent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.04549\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multiagent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.04549","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity
Altruistic cooperation is costly yet socially desirable. As a result, agents
struggle to learn cooperative policies through independent reinforcement
learning (RL). Indirect reciprocity, where agents consider their interaction
partner's reputation, has been shown to stabilise cooperation in homogeneous,
idealised populations. However, more realistic settings are comprised of
heterogeneous agents with different characteristics and group-based social
identities. We study cooperation when agents are stratified into two such
groups, and allow reputation updates and actions to depend on group
information. We consider two modelling approaches: evolutionary game theory,
where we comprehensively search for social norms (i.e., rules to assign
reputations) leading to cooperation and fairness; and RL, where we consider how
the stochastic dynamics of policy learning affects the analytically identified
equilibria. We observe that a defecting majority leads the minority group to
defect, but not the inverse. Moreover, changing the norms that judge in and
out-group interactions can steer a system towards either fair or unfair
cooperation. This is made clearer when moving beyond equilibrium analysis to
independent RL agents, where convergence to fair cooperation occurs with a
narrower set of norms. Our results highlight that, in heterogeneous populations
with reputations, carefully defining interaction norms is fundamental to tackle
both dilemmas of cooperation and of fairness.