MULTI AGENT DEEP LEARNING WITH COOPERATIVE COMMUNICATION

David Simões

doi:10.2478/jaiscr-2020-0013

MULTI AGENT DEEP LEARNING WITH COOPERATIVE COMMUNICATION

2020-05-23

6

OA

AI

DOI：10.2478/jaiscr-2020-0013

Original

Original request for help

Save

Abstract

En 中文

We consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously. A3C2 uses a centralized learning, distributed execution paradigm, supports independent agents, dynamic team sizes, partially-observable environments, and noisy communications. We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments.

Keywords:

multi-agent systems

deep reinforcement learning

centralized learning

MULTI AGENT DEEP LEARNING WITH COOPERATIVE COMMUNICATION

Abstract

Journal

Organization