Unity Machine Learning Agents

categorie

Unity Machine Learning Agents

Nell'ultima versione del ML-Agents Toolkit (v0.14), è stata aggiunta una funzione di auto-play che permette di fare il training ad agenti competitivi che diventano avversari nei giochi (come nei giochi a somma zero, dove il guadagno di un agente è esattamente la perdita dell'altro agente).

Nell'articolo Training intelligent adversaries using self-play with ML-Agents, viene fornita una panoramica dell'auto-play e mostrato come questo permette un allenamento stabile ed efficace sull'ambiente demo del Soccer del Toolkit dei ML-Agents.

Unity ML Home
Releases - release 1.0 - may 2020
ML-Agents forum
Learn to create AI in Unity ML using Deep Reinforcement Learning
Unity Machine Learning Agents


Unity ML-Agents 1.0 - Training your first A.I

Unity ML Agents Tutorial - Penguins (FULL WALKTHROUGH)

Unity3D+ML-Agents Creating a Scene and Training an Agent Basics (RollerBall Tutorial)

Add new comment

The content of this field is kept private and will not be shown publicly.

Full HTML 2

  • Web page addresses and email addresses turn into links automatically.
  • Lines and paragraphs break automatically.

Filtered HTML

  • Web page addresses and email addresses turn into links automatically.
  • Allowed HTML tags: <a href hreflang> <em> <strong> <cite> <blockquote cite> <code> <ul type> <ol start type='1 A I'> <li> <dl> <dt> <dd> <h2 id='jump-*'> <h3 id> <h4 id> <h5 id> <h6 id>
  • Lines and paragraphs break automatically.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.