Emergent Coordination Through Competition

02/19/2019
by   Siqi Liu, et al.
2

We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, not themselves conducive to co-operative behavior, can lead to long-horizon team behavior. We further apply an evaluation scheme, grounded by game theoretic principals, that can assess agent performance in the absence of pre-defined evaluation tasks or human baselines.

READ FULL TEXT

page 5

page 6

page 10

page 19

research
09/19/2018

Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning

We present an effective technique for training deep learning agents capa...
research
11/27/2015

Multiagent Cooperation and Competition with Deep Reinforcement Learning

Multiagent systems appear in most social, economical, and political situ...
research
07/06/2020

Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams

Multi agent strategies in mixed cooperative-competitive environments can...
research
04/13/2021

Two-stage training algorithm for AI robot soccer

In multi-agent reinforcement learning, the cooperative learning behavior...
research
09/17/2019

Emergent Tool Use From Multi-Agent Autocurricula

Through multi-agent competition, the simple objective of hide-and-seek, ...
research
07/27/2021

Open-Ended Learning Leads to Generally Capable Agents

In this work we create agents that can perform well beyond a single, ind...
research
08/06/2019

Promoting Coordination through Policy Regularization in Multi-Agent Reinforcement Learning

A central challenge in multi-agent reinforcement learning is the inducti...

Please sign up or login with your details

Forgot password? Click here to reset