Should We Aim For Humain-AI Coordination Instead Of Human-AI Confrontation?

Therefore Human-AI and more generally multi-agent coordination will be at the center of our interactions with machines in the future.

The problem with arbitrary conventions is that when paired with other agents, the first agent would rely on those conventions to reach its target resulting in poor performance.

The work done on the machine theory of mind was able to improve decision-making in complex multi-agent tasks.

In this respect, the pursuit of a machine theory of mind is about building the missing interface between machines and human expectations.

One of the most impressive recent experiences was the construction of a Dota 2 AI.

One way to train and coordinate different agents is the Single Play (SP) method. The idea is to train an agent with duplicates of itself and make all the agents work in coordination.

The Other Play method tackles this arbitrary convention issue by integrating symmetry transformation.

Agent communication is also a key part of this field and work has already been realized both in free communication and in costly communication between agents.

Should we aim for Humain-AI coordination instead of Human-AI confrontation?

Written by Adam Rida




Engineering student in Applied mathematics and Data Science

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

AI & Law: Evidentiary Admissibility Of Machine Learning

The Recession is in the Details

AI in Business: Think Big and Scale with Intention

Hacking Chatbots: Experimenting with a Product Mindset

Re: Audio Intelligence

AI & Law: The Saga Of AI Maximizing Paperclips

An Understandable Explanation About Zero Knowledge Proofs (ZPK), Plus More Including Blockchain, AI

Google I/O 2018 got me worried and it may you too

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Adam Rida

Adam Rida

Engineering student in Applied mathematics and Data Science

More from Medium

CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous…

Memorizing Transformers ICLR 2022 Paper by Google

Review: Image2StyleGAN — Embedding An Image Into StyleGAN.

Understanding Style Transfer