From the moment we introduced it last September, the developer community has wholeheartedly embraced the ML-Agents Toolkit beta. We’ve seen... さらに読む
Solving sparse-reward tasks with Curiosity
We just released the new version of ML-Agents toolkit (v0.4), and one of the new features we are excited to share with everyone is the ability to train agents with an additional curiosity-based intrinsic reward. Since there is a lot to unpack in this feature, I wanted to write... さらに読む
We just released the new version of ML-Agents toolkit (v0.4), and one of the new features we are excited to share with everyone is the ability to train agents with an additional curiosity-based intrinsic reward. Since there is a lot to unpack in this feature, I wanted to write... さらに読む
Unity ML-Agents Toolkit v0.4 and Udacity Deep Reinforcement Learning Nanodegree
We are happy to announce the release of the latest version of ML-Agents Toolkit: v0.4. It contains a number of features, which we hope everyone will enjoy. It includes... さらに読む
Unity における模倣学習 ― ワークフロー
ML-Agents v0.3 ベータ版が公開され、機械学習を新しく様々な形でプロジェクトに使用できるようになりました。ゲーム開発、シミュレーション、アカデミック、その他どんなタイプのプロジェクトにも、仮想環境内へのニューラルネットワークを使用は利益をもたらします。 この最新版が公開される前から ML-Agents を使用されていた皆... さらに読む
ML-Agents v0.3 ベータ版の公開 ― 模倣学習、フィードバックに基づいた機能などを搭載
ML-Agents チームの提供するツールキットの最新版、v0.3が公開されました。 ML-Agents v0.3 はこれまでの ML-Agents チームからのリリースの中で最大級のものです。これに含まれる主要な機能の多くは、コミュニティの皆様からのフィードバックを基に開発されたものです。今回の新機能の主な目的は、模倣学習、マルチ... さらに読む
Every year 1.25 million people are killed in traffic accidents. In 2016, road crashes resulted in 40,000 deaths and 4.6 million injuries in ... さらに読む
The Machine Learning team at Unity is happy to announce the release of a new version of Unity Machine Learning Agents Toolkit – v0.2 Beta! W... さらに読む
Our two previous blog entries implied that there is a role games can play in driving the development of Reinforcement Learning algorithms. A... さらに読む
Welcome to the second entry in the Unity AI Blog series! For this post, I want to pick up where we left off last time, and talk about how to... さらに読む
Who are these blog entries for? It is our objective to inform Unity Game Developers about the power of AI and ML approaches in game develop... さらに読む