Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others. In reinforcement learning, SVO has been instantiated as an intrinsic motivation that remaps an agent's rewards based on particular target distributions of group reward. 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. Our work extends this body of results and demonstrates that (1) heterogeneous SVO leads to meaningfully diverse policies across a range of incentive structures in sequential social dilemmas, as measured by task-specific diversity metrics; and (2) learning a best response to such policy diversity leads to better zero-shot generalization in some situations. 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.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityZero-shot GeneralizationSimilar Papers 제목 키워드 기반
Learning Roles with Emergent Social Value Orientations
Social dilemmas can be considered situations where individual rationality leads to collective irrationality. The multi-agent reinforcement learning community has leveraged ideas from social science, such as social value …
Multi-agent Reinforcement LearningRole EmbeddingHeterogeneous Value Alignment Evaluation for Large Language Models
The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. However, current methodologies typically attempt to assign value as an attribute to LLMs, yet lac…
AttributeSocial diversity and social preferences in mixed-motive reinforcement learning
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 ha…
Diversityreinforcement-learningReinforcement LearningReinforcement Learning (RL)Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
While recent research has systematically documented political orientation in large language models (LLMs), existing evaluations rely primarily on direct probing or demographic persona engineering to surface ideological b…
MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussions
Moral values play a fundamental role in how we evaluate information, make decisions, and form judgements around important social issues. Controversial topics, including vaccination, abortion, racism, and sexual orientati…
Domain AdaptationLanguage ModelingLanguage Modellingzero-shot-classification+1