CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-05-09 15:12:29 +08:00
Code Issues Projects Releases Wiki Activity

Add WIP bonus 3

Browse Source
This commit is contained in:
Thomas Simonini
2023-02-01 11:53:24 +01:00
parent 2b1d7e3581
commit 1800f755d3
4 changed files with 35 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
units/en/_toctree.yml
View File

@@ -162,6 +162,14 @@
title: Conclusion
- local: unit6/additional-readings
title: Additional Readings
- title: Bonus Unit 3. AI vs. AI Challenge, Snowball Fight
sections:
- local: unitbonus3/introduction
title: Introduction
- local: unitbonus3/hands-on
title: AI vs. AI Challenge Snowball Fight
- local: unitbonus3/conclusion
title: Conclusion
- title: What's next? New Units Publishing Schedule
sections:
- local: communication/publishing-schedule

11
units/en/unitbonus3/conclusion.mdx Normal file
View File

@@ -0,0 +1,11 @@
# Conclusion
That’s all for today. Congrats on finishing this bonus unit and the tutorial!
The best way to learn is to practice and try stuff. **Why not training another agent with a different configuration?**
And don’t hesitate from time to time to check the [leaderboard](https://huggingface.co/spaces/huggingface-projects/AIvsAI-Snowballfight)
See you on Unit 8 🔥,
## Keep Learning, Stay awesome 🤗

1
units/en/unitbonus3/hands-on.mdx Normal file
View File

@@ -0,0 +1 @@
# Hands-on

15
units/en/unitbonus3/introduction.mdx Normal file
View File

@@ -0,0 +1,15 @@
# Introduction
<img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit11/thumbnail.png" alt="Thumbnail"/>
In the last unit, we trained agents to play soccer. Because this was a 2vs2 mode (with 2 agents per team), we wanted to train cooperative behavior inside the team, which was made possible by MA-POCA (Multi-Agent Posthonomous Credit Assignment) algorithm.
Today, as a bonus unit, we will train agents to learn to play snowball fight.
Snowball Fight is a game made by us with Unity ML-Agents, where you shoot snowballs against a Deep Reinforcement Learning agent.
And by pushing your trained model to the Hub, you’re going to participate in this optional **AI vs. AI challenge** where your trained agent will compete against other classmates’ agents every day and be ranked on a [new leaderboard](https://huggingface.co/spaces/huggingface-projects/AIvsAI-Snowballfight).
<img src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit11/snowballtarget.png" alt="Snowballfight"/>
So let's get started,