Inscrever-se em

Training your agents 7 times faster with ML-Agents

+1 novembro 11, 2019Responder

In version 0.8 of ML-Agents, we introduced the ability to train agents using multiple Unity instances on a single machine. We worked with our partner JamCity to train agents to play levels of their bubble shooter game, Snoopy Pop, and showed that this improvement enabled agents t... Ler mais

In version 0.8 of ML-Agents, we introduced the ability to train agents using multiple Unity instances on a single machine. We worked with our partner JamCity to train agents to play levels of their bubble shooter game, Snoopy Pop, and showed that this improvement enabled agents t... Ler mais

The AI@Unity interns help shape the world

+3 outubro 21, 20193

Every Summer, we recruit interns to help us deliver on our mission to empower Unity developers with AI and Machine Learning tools and services. Last summer, the AI@Unity ... Ler mais

Announcing the Obstacle Tower Challenge winners and open source release

+1 agosto 7, 20199

After six months of competition (and a few last-minute submissions), we are happy to announce the conclusion and winners of the Obstacle Tower Challenge. We want to thank... Ler mais

Obstacle Tower Challenge Round 2 begins today

+1 maio 15, 20192

In February, we launched the first round of the Obstacle Tower Challenge. Since the closing of the round, we have received 2000+ entries from 350+ teams. We want to thank... Ler mais

Unity ML-Agents Toolkit v0.8: Faster training on real games

+3 abril 15, 20199

Today, we are releasing a new update to the Unity ML-Agents Toolkit that enables faster training by launching multiple Unity simulations run... Ler mais

Unity ML-Agents Toolkit v0.7: A leap towards cross-platform inference

+1 março 1, 201910

Today, we're making a major upgrade to the Unity ML-Agents Toolkit to leverage the Unity Inference Engine, a new library that enables cross-... Ler mais

The Obstacle Tower Challenge is live!

fevereiro 18, 20195

Three weeks ago we announced the release of the Obstacle Tower Environment, a new benchmark for Artificial Intelligence (AI) research built ... Ler mais

Obstacle Tower Challenge: Test the limits of intelligence systems

janeiro 28, 201914

Today we are announcing the upcoming launch of the Obstacle Tower Challenge: a first-of-its-kind artificial intelligence challenge designed ... Ler mais

Fostering AI Research: Meet us at AAAI-19

+1 janeiro 18, 20192

Last month, several members from the AI @ Unity team were present at NeurIPS in Montreal. At the Unity booth, we had the opportunity to meet... Ler mais

ML-Agents Toolkit v0.6: Improved usability of Brains and Imitation Learning

dezembro 17, 20184

We’ve added a two new enhancements in the Unity ML-Agents Toolkit v0.6 based on your feedback! The first enhancement improves the usability ... Ler mais

Introducing Unity’s Guiding Principles for Ethical AI

novembro 28, 20185

At Unity, we fundamentally believe the world is a better place with more creators in it. It’s our mission every day to democratize developme... Ler mais

Puppo, The Corgi: Cuteness Overload with the Unity ML-Agents Toolkit

+1 outubro 2, 201810

Building a game is a creative process that involves many challenging steps including defining the game concept and logic, building assets an... Ler mais

Unity and DeepMind partner to advance AI research

setembro 26, 20184

Today we are announcing our collaboration with DeepMind, a world leader in artificial intelligence research. The partnership will enable Dee... Ler mais