Related papers: Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition

Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition

URL: http://arxiv.org/abs/2302.04944v2
Date: Thu, 15 Feb 2024 17:43:25 GMT
Title: Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition
Authors: Elliot Fosong, Arrasy Rahman, Ignacio Carlucho, Stefano V. Albrecht
Abstract summary: We propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collectively fine-tuned to solve the more complex target task.
Score: 11.998708550268978
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collectively fine-tuned to solve the more complex target task. We show empirically that such approaches can greatly reduce the number of timesteps required to solve a complex target task relative to training from-scratch. However, we also identify and investigate two problems with naive implementations of approaches based on sub-task decomposition, and propose a simple and scalable method to address these problems which augments existing actor-critic algorithms. We demonstrate the empirical benefits of our proposed method, enabling sub-task decomposition approaches to be deployed in diverse multi-agent tasks.