Learning Existing Social Conventions Via Observationally Augmented Self-play

Abstract

In order for artificial agents to coordinate effectively with people, they must act consistently with existing conventions (e.g. how to navigate in traffic, which language to speak, or how to coordinate with teammates). A group's conventions can be viewed as a choice of equilibrium in a coordination game. We consider the problem of an agent learning a policy for a coordination game in a simulated environment and then using this policy when it enters an existing group. When there are multiple possible conventions we show that learning a policy via multi-agent reinforcement learning (MARL) is likely to find policies which achieve high payoffs at training time but fail to coordinate with the real group into which the agent enters. We assume access to a small number of samples of behavior from the true convention and show that we can augment the MARL objective to help it find policies consistent with the real group's convention. In three environments from the literature - traffic, communic

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keylerer2018learning

Related papers

• Adversarially Guided Self-play For Adopting Social Conventions (2020)0.00
• Generalized Beliefs For Cooperative AI (2022)0.00
• Model-free Conventions In Multi-agent Reinforcement Learning With Heterogeneous Preferences (2020)0.00
• Modeling The Formation Of Social Conventions From Embodied Real-time Interactions (2018)7.50
• Role Play: Learning Adaptive Role-specific Strategies In Multi-agent Interactions (2024)0.00
• Promoting Coordination Through Policy Regularization In Multi-agent Deep Reinforcement Learning (2019)0.00
• Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
• Stackelberg Games For Learning Emergent Behaviors During Competitive Autocurricula (2023)5.84