Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

TL;DR

This paper introduces simple, histogram-based local communication protocols for multi-robot swarms, enabling deep reinforcement learning to develop decentralized control policies for complex collaborative tasks.

Contribution

It proposes novel, easy-to-define communication protocols that improve RL-based decentralized control in swarm systems, with a focus on task-specific information transmission.

Findings

Protocols facilitate learning of complex behaviors like formation building.

Histogram-based communication improves policy effectiveness.

Evaluation shows protocols' impact on swarm coordination in simulation.

Abstract

Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communication protocols can be defined more easily using prior knowledge about the given task. In this paper, we propose a number of simple communication protocols that can be exploited by deep reinforcement learning to find decentralized control policies in a multi-robot swarm environment. The protocols are based on histograms that encode the local neighborhood relations of the agents and can also transmit task-specific information, such as the shortest distance and direction to a desired target. In our framework, we use an adaptation of Trust Region Policy Optimization to learn complex collaborative tasks, such as formation building and building a communication link. We evaluate our findings in a simulated 2D-physics environment, and compare the implications of different communication protocols.