Transformers As Game Players: Provable In-context Game-playing Capabilities Of Pre-trained Models

Abstract

The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years. While theoretical understanding has been obtained for ICL in reinforcement learning (RL), the previous results are largely confined to the single-agent setting. This work proposes to further explore the in-context learning capabilities of pre-trained transformer models in competitive multi-agent games, i.e., in-context game-playing (ICGP). Focusing on the classical two-player zero-sum games, theoretical guarantees are provided to demonstrate that pre-trained transformers can provably learn to approximate Nash equilibrium in an in-context manner for both decentralized and centralized learning settings. As a key part of the proof, constructional results are established to demonstrate that the transformer architecture is sufficiently rich to realize celebrated multi-agent game-playing algorithms, in particular, decentralized V-learning and cen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshi2024transformers

Related papers

• Transformers Can Learn Temporal Difference Methods For In-context Reinforcement Learning (2024)0.00
• Transformer Based Reinforcement Learning For Games (2019)0.00
• From Memories To Maps: Mechanisms Of In-context Reinforcement Learning In Transformers (2025)0.00
• Transformers Are Sample-efficient World Models (2022)0.00
• In-context Exploiter For Extensive-form Games (2024)0.00
• No-regret Learning In Games Is Turing Complete (2022)0.00
• Updet: Universal Multi-agent Reinforcement Learning Via Policy Decoupling With Transformers (2021)0.00
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00