Learning Transferable Cooperative Behavior in Multi-Agent Teams (2019-06-04T00:00:00.000000Z)

TL;DR

A shared agent-entity graph is proposed, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other, allowing agents to selectively attend to different parts of the environment, while also introducing invariance to the number of agents or entities present in the system as well as permutation invariance.

Abstract

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. To better utilize the inherent structure of our environment, we propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other, allowing agents to selectively attend to different parts of the environment, while also introducing invariance to the number of agents or entities present in the system as well as permutation invariance. We present state-of-the-art results on coverage, formation and line control tasks for multi-agent teams in a fully decentralized execution framework.

Authors

Sumit Kumar

2 papers

K. Sycara

2 papers

Akshat Agarwal

1 papers

TL;DR

Abstract

Authors

References46 items

Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation

TarMAC: Targeted Multi-Agent Communication

Pommerman: A Multi-Agent Playground

Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Benchmark

Community Regularization of Visually-Grounded Dialog

Learning Attentional Communication for Multi-Agent Cooperation

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

Proximal Policy Optimization Algorithms

VAIN: Attentional Multi-agent Predictive Modeling

Value-Decomposition Networks For Cooperative Multi-Agent Learning

Attention is All you Need

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Counterfactual Multi-Agent Policy Gradients

Automated sequencing of swarm behaviors for supervisory control of robotic swarms

Neural Message Passing for Quantum Chemistry

Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability

Emergence of Grounded Compositional Language in Multi-Agent Populations

Semi-Supervised Classification with Graph Convolutional Networks

A Concise Introduction to Decentralized POMDPs

Learning Multiagent Communication with Backpropagation

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Mastering the game of Go with deep neural networks and tree search

Multiagent cooperation and competition with deep reinforcement learning

Continuous control with deep reinforcement learning

High-Dimensional Continuous Control Using Generalized Advantage Estimation

Human-level control through deep reinforcement learning

Adam: A Method for Stochastic Optimization

Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Playing Atari with Deep Reinforcement Learning

Graph Theoretic Methods in Multiagent Networks

Curriculum learning

Hysteretic q-learning :an algorithm for decentralized reinforcement learning in cooperative multi-agent teams

Naive control of the double integrator

Markov Games as a Framework for Multi-Agent Reinforcement Learning

Q-learning

The Hungarian method for the assignment problem

AlphaStar: Mastering the Real-Time Strategy Game StarCraft II. https://deepmind.com/blog/ alphastar-mastering-real-time-strategy-game-starcraft-ii/, 2019

Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation

Pytorch implementations of reinforcement learning algorithms. https: //github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail, 2018

Dropout: a simple way to prevent neural networks from overfitting

The Graph Neural Network Model

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Multi Agent Reinforcement Learning Independent vs Cooperative Agents

Introduction to reinforcement learning, volume 135

Behavior-based formation control for multirobot teams

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names