D3C: Reducing the Price of Anarchy in Multi-Agent Learning

10/01/2020
by   Ian Gemp, et al.
0

Even in simple multi-agent systems, fixed incentives can lead to outcomes that are poor for the group and each individual agent. We propose a method, D3C, for online adjustment of agent incentives that reduces the loss incurred at a Nash equilibrium. Agents adjust their incentives by learning to mix their incentive with that of other agents, until a compromise is reached in a distributed fashion. We show that D3C improves outcomes for each agent and the group as a whole on several social dilemmas including a traffic network with Braess's paradox, a prisoner's dilemma, and several reinforcement learning domains.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/11/2020

Multi-Agent Informational Learning Processes

We introduce a new mathematical model of multi-agent reinforcement learn...
04/06/2020

Using Multi-Agent Reinforcement Learning in Auction Simulations

Game theory has been developed by scientists as a theory of strategic in...
01/30/2019

Coordinating the Crowd: Inducing Desirable Equilibria in Non-Cooperative Systems

Many real-world systems such as taxi systems, traffic networks and smart...
03/13/2018

Decentralised Learning in Systems with Many, Many Strategic Agents

Although multi-agent reinforcement learning can tackle systems of strate...
03/18/2019

Surrogate Optimal Control for Strategic Multi-Agent Systems

This paper studies how to design a platform to optimally control constra...
09/26/1998

Learning Nested Agent Models in an Information Economy

We present our approach to the problem of how an agent, within an econom...
03/16/2020

Value Variance Minimization for Learning Approximate Equilibrium in Aggregation Systems

For effective matching of resources (e.g., taxis, food, bikes, shopping ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.