Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games

• Main Authors: BUI, The Viet, MAI, Tien, NGUYEN, Hong Thanh
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Multi-agent reinforcement learning; Imitation learning; Inverse Q learning; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9788; https://ink.library.smu.edu.sg/context/sis_research/article/10788/viewcontent/NeurIPS2024___IL_for_Competitive_Multi_agent_Games__1_.pdf
• Institution: Singapore Management University

Training agents in multi-agent games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by strategies of opponents. Existing methods often struggle with slow convergence and instability. To address these challenges, we harness the potential of imitation learning (IL) to comprehend and anticipate actions of the opponents, aiming to mitigate uncertainties with respect to the game dynamics. Our key contributions include: (i) a new multi-agent IL model for predicting next moves of the opponents --- our model works with hidden actions of opponents and local observations; (ii) a new multi-agent reinforcement learning (MARL) algorithm that combines our IL 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). Experimental results show that our approach achieves superior performance compared to state-of-the-art MARL algorithms.