OpenAI Retro Contest – Compilation of Reinforcement Learning Write-Ups

Compilation of all the Write-Ups which i found on Discord/Internet for the OpenAI Reinforcement Learning Challenge.

Leaderboard status after the contest has ended.

1. World Models applied to Sonic

https://dylandjian.github.io/world-models/

Github link: https://github.com/dylandjian/retro-contest-sonic

Write-Up based on the World Models paper: https://arxiv.org/pdf/1803.10122.pdf

2. Train a Reinforcement Learning agent to play custom levels of Sonic the Hedgehog with Transfer Learning

https://flyyufelix.github.io/2018/06/11/sonic-rl.html

Write-Up on Transfer Learning. This implementation is for the 5th place in leaderboard with a score of 5522.

3. Using Deep Reinforcement Learning to Play Sonic the Hedgehog

View story at Medium.com

 

Another algorithm based on the World Models paper: https://worldmodels.github.io/

4. world-models-sonic-pytorch

https://gitlab.com/wassname/world-models-pytorch

Implementation of World Models using pytorch.

5. OpenAI Retro – Collision Maps

https://mikelyons.org/2018/05/20/Retro-OpenAI-Collision-Map.html

Visual Approach.

6. Retro contest solution

https://github.com/fgvbrt/retro_contest

Source code for #8 place in Leaderboard and score of 5365.36

7. My final submission: the Improved JERK.

View story at Medium.com

Implementation based on JERK algorithm.

8. OpenAI Retro Contest – Guide on “How to Score 6k points on Leaderboard in AI Challange”

OpenAI Retro Contest – Guide on “How to Score 6k points on Leaderboard in AI Challange”

My try on the contest with tuning of the hyperparamters.

9. Agents for OpenAI Retro Contest

Source Code: https://github.com/seungjaeryanlee/retro-agents

WriteUp: https://github.com/seungjaeryanlee/retro-agents/blob/master/results/writeup/iclr2018_conference.pdf

Blog Post: https://www.endtoend.ai/blog/i-learned-dqns-with-openai-competition

Well documented approach using Rainbow DQN.

Results: https://github.com/seungjaeryanlee/retro-agents/blob/master/results/RESULTS.md

10. OpenAI Retro Contest Report

View story at Medium.com

(15th place): Rainbow DQN with NoisyNet exploration and expert replay

 

Those are all the write-ups which i was able to find.

Thanks for sharing those write-ups!

Those are a great way to learn about Reinforcement Learning algorithms and how we could improve our approaches.

 

Leave a Reply

Your email address will not be published. Required fields are marked *