Imitation Learning as a Tool for Modeling Cooperative Agent Games
DOI:
https://doi.org/10.47611/jsrhs.v13i1.6184Keywords:
swarm theory, game theory, machine learning, cooperative agent games, cooperative agent, imitation learning, reinforcement learning, markov decision processesAbstract
The modern day sees constant application of team-level cooperation, and game theory offers a way to model these tasks in a way that provides applicable results. We created a game using Python 3 that had 3 or more agents from one team surround an agent from another team to consume them, with the end goal of consuming the other team. These agents were then trained in a centralized training, decentralized execution schema to mimic an expert’s behavior using imitation learning. Agents trained under this imitation learning schema performed significantly better than agents who followed a random policy, and as more training was supplied to the agents to learn off of, the agents performed better compared to other lesser trained teams.
Downloads
References or Bibliography
Jin, J. (n.d.). Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising.
arXiv.
Leibo, J. (n.d.). A multi-agent reinforcement learning model of common-pool resource appropriation.
arXiv.
Lowe, R. (n.d.). Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. arXiv.
Shalev-Shwartz, S. (n.d.). Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving.
arXiv.
Published
How to Cite
Issue
Section
Copyright (c) 2024 Nikhil Alladi; Sam Showalter
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
