Multi-Agent Pattern Formation with Deep Reinforcement Learning (Student Abstract)

We propose a decentralized multi-agent deep reinforcement learning architecture to investigate pattern formation under the local information provided by the agents' sensors. It consists of tasking a large number of homogeneous agents to move to a set of specified goal locations, addressing both the assignment and trajectory planning sub-problems concurrently. We then show that agents trained on random patterns can organize themselves into very complex shapes.

Download Full-text

Adaptive Load Balancing: A Study in Multi-Agent Learning

Journal of Artificial Intelligence Research ◽

10.1613/jair.121 ◽

1995 ◽

Vol 2 ◽

pp. 475-500 ◽

Cited By ~ 80

Author(s):

A. Schaerf ◽

Y. Shoham ◽

M. Tennenholtz

Keyword(s):

Reinforcement Learning ◽

Load Balancing ◽

Distributed System ◽

Adaptive Behavior ◽

Local Information ◽

System Efficiency ◽

Agent Learning ◽

Multi Agent ◽

Explicit Communication

We study the process of multi-agent reinforcement learning in the context ofload balancing in a distributed system, without use of either centralcoordination or explicit communication. We first define a precise frameworkin which to study adaptive load balancing, important features of which are itsstochastic nature and the purely local information available to individualagents. Given this framework, we show illuminating results on the interplaybetween basic adaptive behavior parameters and their effect on systemefficiency. We then investigate the properties of adaptive load balancing inheterogeneous populations, and address the issue of exploration vs.exploitation in that context. Finally, we show that naive use ofcommunication may not improve, and might even harm system efficiency.

Download Full-text

Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing

IEEE Transactions on Cognitive Communications and Networking ◽

10.1109/tccn.2020.3027695 ◽

2020 ◽

pp. 1-1

Author(s):

Liang Wang ◽

Kezhi Wang ◽

Cunhua Pan ◽

Wei Xu ◽

Nauman Aslam ◽

...

Keyword(s):

Reinforcement Learning ◽

Trajectory Planning ◽

Edge Computing ◽

Mobile Edge Computing ◽

Multi Agent ◽

Multi Uav

Download Full-text

Deep Reinforcement Learning Algorithms for Multiple Arc-Welding Robots

Frontiers in Control Engineering ◽

10.3389/fcteg.2021.632417 ◽

2021 ◽

Vol 2 ◽

Author(s):

Lei-Xin Xu ◽

Yang-Yang Chen

Keyword(s):

Reinforcement Learning ◽

Arc Welding ◽

Distributed Simulation ◽

Local Information ◽

Time Varying ◽

Robot Systems ◽

Policy Gradient ◽

Distributed Execution ◽

Multi Agent ◽

Simulation Results

The applications of the deep reinforcement learning method to achieve the arcs welding by multi-robot systems are presented, where the states and the actions of each robot are continuous and obstacles are considered in the welding environment. In order to adapt to the time-varying welding task and local information available to each robot in the welding environment, the so-called multi-agent deep deterministic policy gradient (MADDPG) algorithm is designed with a new set of rewards. Based on the idea of the distributed execution and centralized training, the proposed MADDPG algorithm is distributed. Simulation results demonstrate the effectiveness of the proposed method.

Download Full-text