Learning Strategy Representation For Imitation Learning In Multi-agent Games

Abstract

The offline datasets for imitation learning (IL) in multi-agent games typically contain player trajectories exhibiting diverse strategies, which necessitate measures to prevent learning algorithms from acquiring undesirable behaviors. Learning representations for these trajectories is an effective approach to depicting the strategies employed by each demonstrator. However, existing learning strategies often require player identification or rely on strong assumptions, which are not appropriate for multi-agent games. Therefore, in this paper, we introduce the Strategy Representation for Imitation Learning (STRIL) framework, which (1) effectively learns strategy representations in multi-agent games, (2) estimates proposed indicators based on these representations, and (3) filters out sub-optimal data using the indicators. STRIL is a plug-in method that can be integrated into existing IL algorithms. We demonstrate the effectiveness of STRIL across competitive multi-agent scenarios, includi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylei2024learning

Related papers

• Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games (2023)0.00
• Learning Policy Representations In Multiagent Systems (2018)0.00
• Learning Mixed Strategies In Trajectory Games (2022)0.00
• Independent Generative Adversarial Self-imitation Learning In Cooperative Multiagent Systems (2019)0.00
• Learning Meta Representations For Agents In Multi-agent Reinforcement Learning (2021)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00
• Learning From Good Trajectories In Offline Multi-agent Reinforcement Learning (2022)5.24