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

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 addre...

Full description

Saved in:
Bibliographic Details
Main Authors: BUI, The Viet, MAI, Tien, NGUYEN, Hong Thanh
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
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
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10788
record_format dspace
spelling sg-smu-ink.sis_research-107882024-12-16T01:53:59Z Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games BUI, The Viet MAI, Tien NGUYEN, Hong Thanh 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. 2024-12-01T08:00:00Z text application/pdf 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 http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Multi-agent reinforcement learning Imitation learning Inverse Q learning Artificial Intelligence and Robotics Computer Sciences
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Multi-agent reinforcement learning
Imitation learning
Inverse Q learning
Artificial Intelligence and Robotics
Computer Sciences
spellingShingle Multi-agent reinforcement learning
Imitation learning
Inverse Q learning
Artificial Intelligence and Robotics
Computer Sciences
BUI, The Viet
MAI, Tien
NGUYEN, Hong Thanh
Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
description 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.
format text
author BUI, The Viet
MAI, Tien
NGUYEN, Hong Thanh
author_facet BUI, The Viet
MAI, Tien
NGUYEN, Hong Thanh
author_sort BUI, The Viet
title Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
title_short Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
title_full Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
title_fullStr Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
title_full_unstemmed Mimicking to dominate: Imitation learning strategies for success in multiagent competitive games
title_sort mimicking to dominate: imitation learning strategies for success in multiagent competitive games
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url 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
_version_ 1819113139034128384