Social diversity and social preferences in mixed-motive reinforcement learning

• URL: http://arxiv.org/abs/2002.02325v2
• Date: Wed, 12 Feb 2020 19:35:05 GMT
• Title: Social diversity and social preferences in mixed-motive reinforcement learning
• Authors: Kevin R. McKee, Ian Gemp, Brian McWilliams, Edgar A. Du\'e\~nez-Guzm\'an, Edward Hughes, and Joel Z. Leibo
• Abstract summary: Studies of reinforcement learning in mixed-motive games have primarily leveraged homogeneous approaches. We study the effect of population heterogeneity on mixed-motive reinforcement learning.
• Score: 11.010593309447067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent research on reinforcement learning in pure-conflict and pure-common interest games has emphasized the importance of population heterogeneity. In contrast, studies of reinforcement learning in mixed-motive games have primarily leveraged homogeneous approaches. Given the defining characteristic of mixed-motive games--the imperfect correlation of incentives between group members--we study the effect of population heterogeneity on mixed-motive reinforcement learning. We draw on interdependence theory from social psychology and imbue reinforcement learning agents with Social Value Orientation (SVO), a flexible formalization of preferences over group outcome distributions. We subsequently explore the effects of diversity in SVO on populations of reinforcement learning agents in two mixed-motive Markov games. We demonstrate that heterogeneity in SVO generates meaningful and complex behavioral variation among agents similar to that suggested by interdependence theory. Empirical results in these mixed-motive dilemmas suggest agents trained in heterogeneous populations develop particularly generalized, high-performing policies relative to those trained in homogeneous populations.

Related papers

• The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention [61.80236015147771]
  We quantify the trade-off between using diversity interventions and preserving demographic factuality in T2I models. Experiments on DoFaiR reveal that diversity-oriented instructions increase the number of different gender and racial groups. We propose Fact-Augmented Intervention (FAI) to reflect on verbalized or retrieved factual information about gender and racial compositions of generation subjects in history.
  arXiv  Detail & Related papers  (2024-06-29T09:09:42Z)
• Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents [3.7414804164475983]
  We study the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. We observe several types of non-trivial interactions between pro-social and anti-social agents. We find that certain types of moral agents are able to steer selfish agents towards more cooperative behavior.
  arXiv  Detail & Related papers  (2024-03-07T04:12:24Z)
• Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning [60.058083574671834]
  This paper presents a novel FCCL+, federated correlation and similarity learning with non-target distillation. For heterogeneous issue, we leverage irrelevant unlabeled public data for communication. For catastrophic forgetting in local updating stage, FCCL+ introduces Federated Non Target Distillation.
  arXiv  Detail & Related papers  (2023-09-28T09:32:27Z)
• Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas [15.171556039829161]
  Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others. Prior studies show that groups of agents endowed with heterogeneous SVO learn diverse policies in settings that resemble the incentive structure of Prisoner's dilemma. We show that these best-response agents learn policies that are conditioned on their co-players, which we posit is the reason for improved zero-shot generalization results.
  arXiv  Detail & Related papers  (2023-05-01T11:09:23Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)
• Learning Roles with Emergent Social Value Orientations [49.16026283952117]
  This paper introduces the typical "division of labor or roles" mechanism in human society. We provide a promising solution for intertemporal social dilemmas (ISD) with social value orientations (SVO) A novel learning framework, called Learning Roles with Emergent SVOs (RESVO), is proposed to transform the learning of roles into the social value orientation emergence.
  arXiv  Detail & Related papers  (2023-01-31T17:54:09Z)
• Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization? [90.35044668396591]
  A recurring theme in machine learning is algorithmic monoculture: the same systems, or systems that share components, are deployed by multiple decision-makers. We propose the component-sharing hypothesis: if decision-makers share components like training data or specific models, then they will produce more homogeneous outcomes. We test this hypothesis on algorithmic fairness benchmarks, demonstrating that sharing training data reliably exacerbates homogenization. We conclude with philosophical analyses of and societal challenges for outcome homogenization, with an eye towards implications for deployed machine learning systems.
  arXiv  Detail & Related papers  (2022-11-25T09:33:11Z)
• Sociodemographic inequalities in student achievement: An intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) with application to students in London, England [0.0]
  We study sociodemographic inequalities in student achievement across two cohorts of students in London, England. We find substantial strata-level variation in achievement composed primarily by additive rather than interactive effects. We conclude that policymakers should pay greater attention to multiply marginalized students.
  arXiv  Detail & Related papers  (2022-11-10T16:16:52Z)
• Learning Collective Action under Risk Diversity [68.88688248278102]
  We investigate the consequences of risk diversity in groups of agents learning to play collective risk dilemmas. We show that risk diversity significantly reduces overall cooperation and hinders collective target achievement. Our results highlight the need for aligning risk perceptions among agents or develop new learning techniques.
  arXiv  Detail & Related papers  (2022-01-30T18:21:21Z)
• Improved cooperation by balancing exploration and exploitation in intertemporal social dilemma tasks [2.541277269153809]
  We propose a new learning strategy for achieving coordination by incorporating a learning rate that can balance exploration and exploitation. We show that agents that use the simple strategy improve a relatively collective return in a decision task called the intertemporal social dilemma. We also explore the effects of the diversity of learning rates on the population of reinforcement learning agents and show that agents trained in heterogeneous populations develop particularly coordinated policies.
  arXiv  Detail & Related papers  (2021-10-19T08:40:56Z)
• The Evolutionary Dynamics of Independent Learning Agents in Population Games [21.68881173635777]
  This paper presents a formal relation between processes and the dynamics of independent learning agents in population games. Using a master equation approach, we provide a novel unified framework for characterising population dynamics.
  arXiv  Detail & Related papers  (2020-06-29T14:22:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.