Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Lunjun, Jiang, Weilai, Wang, Yaonan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910761121480704
author Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
author_facet Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
contents In multi-agent reinforcement learning (MARL), the centralized training with decentralized execution (CTDE) framework has gained widespread adoption due to its strong performance. However, the further development of CTDE faces two key challenges. First, agents struggle to autonomously assess the relevance of input information for cooperative tasks, impairing their decision-making abilities. Second, in communication-limited scenarios with partial observability, agents are unable to access global information, restricting their ability to collaborate effectively from a global perspective. To address these challenges, we introduce a novel cooperative MARL framework based on information selection and tacit learning. In this framework, agents gradually develop implicit coordination during training, enabling them to infer the cooperative behavior of others in a discrete space without communication, relying solely on local information. Moreover, we integrate gating and selection mechanisms, allowing agents to adaptively filter information based on environmental changes, thereby enhancing their decision-making capabilities. Experiments on popular MARL benchmarks show that our framework can be seamlessly integrated with state-of-the-art algorithms, leading to significant performance improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15639
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning
Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
Multiagent Systems
Artificial Intelligence
Machine Learning
In multi-agent reinforcement learning (MARL), the centralized training with decentralized execution (CTDE) framework has gained widespread adoption due to its strong performance. However, the further development of CTDE faces two key challenges. First, agents struggle to autonomously assess the relevance of input information for cooperative tasks, impairing their decision-making abilities. Second, in communication-limited scenarios with partial observability, agents are unable to access global information, restricting their ability to collaborate effectively from a global perspective. To address these challenges, we introduce a novel cooperative MARL framework based on information selection and tacit learning. In this framework, agents gradually develop implicit coordination during training, enabling them to infer the cooperative behavior of others in a discrete space without communication, relying solely on local information. Moreover, we integrate gating and selection mechanisms, allowing agents to adaptively filter information based on environmental changes, thereby enhancing their decision-making capabilities. Experiments on popular MARL benchmarks show that our framework can be seamlessly integrated with state-of-the-art algorithms, leading to significant performance improvements.
title Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.15639