Generalized Beliefs For Cooperative AI

Abstract

Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-specialized conventions that make playing with a novel partner difficult. To address this, recent approaches rely on encoding symmetry and convention-awareness into policy training, but these require strong environmental assumptions and can complicate policy training. We therefore propose moving the learning of conventions to the belief space. Specifically, we propose a belief learning model that can maintain beliefs over rollouts of policies not seen at training time, and can thus decode and adapt to novel conventions at test time. We show how to leverage this model for both search and training of a best response over various pools of policies to greatly improve ad-hoc teamplay. We also show how our setup promotes explainability and interpretability of nuanced agent conventions.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymuglich2022generalized

Related papers

• Learning Existing Social Conventions Via Observationally Augmented Self-play (2018)7.81
• Adversarially Guided Self-play For Adopting Social Conventions (2020)0.00
• Behaviour-conditioned Policies For Cooperative Reinforcement Learning Tasks (2021)2.26
• The Yokai Learning Environment: Tracking Beliefs Over Space And Time (2025)0.00
• Multi-agent Cooperative Games Using Belief Map Assisted Training (2024)0.00
• Fictitious Cross-play: Learning Global Nash Equilibrium In Mixed Cooperative-competitive Games (2023)3.58
• Training Generalizable Collaborative Agents Via Strategic Risk Aversion (2026)0.00
• Off-belief Learning (2021)0.00