Differential Advising in Multi-Agent Reinforcement Learning

by   Dayong Ye, et al.

Agent advising is one of the main approaches to improve agent learning performance by enabling agents to share advice. Existing advising methods have a common limitation that an adviser agent can offer advice to an advisee agent only if the advice is created in the same state as the advisee's concerned state. However, in complex environments, it is a very strong requirement that two states are the same, because a state may consist of multiple dimensions and two states being the same means that all these dimensions in the two states are correspondingly identical. Therefore, this requirement may limit the applicability of existing advising methods to complex environments. In this paper, inspired by the differential privacy scheme, we propose a differential advising method which relaxes this requirement by enabling agents to use advice in a state even if the advice is created in a slightly different state. Compared with existing methods, agents using the proposed method have more opportunity to take advice from others. This paper is the first to adopt the concept of differential privacy on advising to improve agent learning performance instead of addressing security issues. The experimental results demonstrate that the proposed method is more efficient in complex environments than existing methods.


page 1

page 2

page 3

page 4


Federated Recommendation System via Differential Privacy

In this paper, we are interested in what we term the federated private b...

Differentially Private Multi-Agent Planning for Logistic-like Problems

Planning is one of the main approaches used to improve agents' working e...

ASCII: ASsisted Classification with Ignorance Interchange

The rapid development in data collecting devices and computation platfor...

Differentially Private LQ Control

As multi-agent systems proliferate and share more and more user data, ne...

Reinforcement Learning on Encrypted Data

The growing number of applications of Reinforcement Learning (RL) in rea...

Defensive Design of Saturating Counters Based on Differential Privacy

The saturating counter is the basic module of the dynamic branch predict...

Please sign up or login with your details

Forgot password? Click here to reset