MAAILGJun 11, 2020

Multi-Agent Informational Learning Processes

arXiv:2006.06870v42 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of understanding information dynamics in multi-agent systems for researchers in AI and reinforcement learning, but it appears incremental as it builds on existing concepts without clear practical applications.

The authors tackled the problem of modeling multi-agent reinforcement learning by introducing the Multi-Agent Informational Learning Processor (MAILP) model, which describes how information evolves and propagates among agents, with the result being a general framework based on the assumption that individual learning slows over time.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes