Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games

Abstract

Training agents in multi-agent competitive games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by opponents' strategies. Existing methods often struggle with slow convergence and instability. To address this, we harness the potential of imitation learning to comprehend and anticipate opponents' behavior, aiming to mitigate uncertainties with respect to the game dynamics. Our key contributions include: (i) a new multi-agent imitation learning model for predicting next moves of the opponents -- our model works with hidden opponents' actions and local observations; (ii) a new multi-agent reinforcement learning algorithm that combines our imitation learning model and policy training into one single training process; and (iii) extensive experiments in three challenging game environments, including an advanced version of the Star-Craft multi-agent challenge (i.e., SMACv2). Experiment

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybui2023mimicking

Related papers

• Imitating Opponent To Win: Adversarial Policy Imitation Learning In Two-player Competitive Games (2022)0.00
• All By Myself: Learning Individualized Competitive Behaviour With A Contrastive Reinforcement Learning Optimization (2023)7.16
• Learning From Learners: Adapting Reinforcement Learning Agents To Be Competitive In A Card Game (2020)0.00
• Learning Strategy Representation For Imitation Learning In Multi-agent Games (2024)0.00
• Decentralized Multi-agents By Imitation Of A Centralized Controller (2019)0.00
• Matching Multiple Experts: On The Exploitability Of Multi-agent Imitation Learning (2026)0.00
• Natural Emergence Of Heterogeneous Strategies In Artificially Intelligent Competitive Teams (2020)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00