Login
Forgot?

Forget your password?
Remembered Password?
  • Blog
    • Clara: A Neural Net Music Generator
      • Project Overview
      • Human or AI
      • Adding a Judge
      • Generating Violin/Piano Duo
      • Composing Music
      • Generating Mozart
      • Music Generation
    • Soccer
      • Adding Simulation Mechanics
      • World Cup Soccer: Team Spirit
      • Multi-Agent Training: Lessons learned from training 3 separate competing networks
    • Other
      • Reinforcement Learning – The Big Picture
      • DL & RL advice
      • Unity ML Agents & Reinforcement Learning
      • Training Neural Nets in the Browser
      • Winemanical Adventures
  • Learning About Deep Learning
  • Neural Gallery
  • Chamber Music
    • Audio
    • Video
  • Blog
    • Clara: A Neural Net Music Generator
      • Project Overview
      • Human or AI
      • Adding a Judge
      • Generating Violin/Piano Duo
      • Composing Music
      • Generating Mozart
      • Music Generation
    • Soccer
      • Adding Simulation Mechanics
      • World Cup Soccer: Team Spirit
      • Multi-Agent Training: Lessons learned from training 3 separate competing networks
    • Other
      • Reinforcement Learning – The Big Picture
      • DL & RL advice
      • Unity ML Agents & Reinforcement Learning
      • Training Neural Nets in the Browser
      • Winemanical Adventures
  • Learning About Deep Learning
  • Neural Gallery
  • Chamber Music
    • Audio
    • Video

Archives

Monthly Archive for: "June, 2018"
Home /
 Multi-Agent Training: Lessons learned from training 3 separate competing networks
0
By mcleavey
In Highlights, Reinforcement Learning, Soccer
Posted June 25, 2018

Multi-Agent Training: Lessons learned from training 3 separate competing networks

Over the course of the weekend, I dug further into my soccer RL project. I realized that while the Striker and Goalie brains had learned very good policies, the Defenders were terrible. Testing [...]

READ MORE
 Unity ML Agents & Reinforcement Learning
0
By mcleavey
In Reinforcement Learning
Posted June 22, 2018

Unity ML Agents & Reinforcement Learning

In honor of the ongoing World Cup, I worked this week on training agents to play soccer as a team. I used the Unity Game Engine and based the scene off of a demo scene in their ML Agent library. [...]

READ MORE
 Reinforcement Learning – The Big Picture
0
By mcleavey
In Background
Posted June 15, 2018

Reinforcement Learning – The Big Picture

So, I survived my first week of studying Reinforcement Learning. I know a good amount of deep learning and I love math, so I assumed RL would be an interesting but fairly comfortable excursion. [...]

READ MORE
 Training Neural Nets in the Browser
3
By mcleavey
In Background
Posted June 8, 2018

Training Neural Nets in the Browser

Two months ago, Google announced its new TensorflowJS, for training and inference in the browser. This opens the door to a lot of amazing web applications. Try out Webcam Pacman and Mobile Phone [...]

READ MORE
 Learning About Deep Learning
11
By mcleavey
In Background
Posted June 1, 2018

Learning About Deep Learning

I’m thrilled to be a part of the Scholars Program this summer at OpenAI (update: I’m continuing on this fall as an OpenAI Fellow!). I was a physics major and I’ve always loved [...]

READ MORE
Copyright All Rights Reserved © 2017
Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text. captcha txt

Start typing and press Enter to search