Cognition-Oriented Multiagent Reinforcement Learning

doi:10.1109/TNNLS.2024.3502176

Cognition-Oriented Multiagent Reinforcement Learning

2025-01-01

0

PRE

AI

DOI：10.1109/TNNLS.2024.3502176

原文链接

原文求助

摘要

En 中文

Inspired by psychological insights into individual behavior, we propose a novel cognition-oriented multiagent reinforcement learning (CORL) framework. CORL equips agents with two distinct types of cognition-situational and self-cognition-derived from local observations. To enhance the informativeness and precision of these cognition types, we introduce two information-theoretical regularizers: one to align situational cognition with the global state and the other to align self-cognition with each agent's identity for improved role differentiation and team coordination. In addition, the centralized training and decentralized execution framework is adopted to train the policy network. Our simulations demonstrate that CORL effectively harnesses local observations for enriched cooperation, leading to pronounced performance improvements, particularly in challenging tasks.

Keyword:

Cognition

Training

Reinforcement learning

Observability

Multi-agent systems

Data mining

Automation

Trajectory

Mutual information

Simulation

Centralized training with decentralized execution

cognition learning

multiagent reinforcement learning (MARL)

mutual information

Cognition-Oriented Multiagent Reinforcement Learning

摘要

期刊

机构

引用论文