DeepAI AI Chat
Log In Sign Up

Multi-Agent Informational Learning Processes

06/11/2020
by   Justin K. Terry, et al.
University of Maryland
0

We introduce a new mathematical model of multi-agent reinforcement learning, the Multi-Agent Informational Learning Processor "MAILP" model. The model is based on the notion that agents have policies for a certain amount of information, models how this information iteratively evolves and propagates through many agents. This model is very general, and the only meaningful assumption made is that learning for individual agents progressively slows over time.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/22/2018

Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients

In this paper, we explore using deep reinforcement learning for problems...
04/20/2022

Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning

Recently, model-based agents have achieved better performance than model...
10/18/2022

RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning

Despite the recent advancement in multi-agent reinforcement learning (MA...
03/06/2022

Recursive Reasoning Graph for Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) provides an efficient way for ...
06/19/2017

VAIN: Attentional Multi-agent Predictive Modeling

Multi-agent predictive modeling is an essential step for understanding p...
10/01/2020

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

Even in simple multi-agent systems, fixed incentives can lead to outcome...
04/27/2020

A Microscopic Epidemic Model and Pandemic Prediction Using Multi-Agent Reinforcement Learning

This paper introduces a microscopic approach to model epidemics, which c...