https://github.com/scottpletcher/deepracer

AWS DeepRacer Experimentation
https://github.com/scottpletcher/deepracer

Last synced: about 13 hours ago
JSON representation

AWS DeepRacer Experimentation

• Host: GitHub
• URL: https://github.com/scottpletcher/deepracer
• Owner: scottpletcher
• License: mit
• Archived: true
• Created: 2019-05-15T15:38:50.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-04-15T03:10:02.000Z (over 4 years ago)
• Last Synced: 2024-08-02T13:19:25.943Z (3 months ago)
• Size: 51.1 MB
• Stars: 276
• Watchers: 18
• Forks: 54
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AWS DeepRacer Experimentation

This is an informal log of my exploration of [AWS DeepRacer](https://aws.amazon.com/deepracer/) training.  I hope this might help out someone just getting started or inspire some different approachs.

## Reward Functions

|Iteration|Model Codename|Strategy| 

| :---: |:---:|:-----|

|1|["PurePursuit"](./iterations/v1-PurePursuit.md)|A Pure Pursuit algorithm inspired approach|

|2|["RacingLine"](./iterations/v2-RacingLine.md)|Use waypoints and lane preference to encourage a racing line|

|3|["GetFast"](./iterations/v3-GetFast.md)|Add an exponential speed component|

|4|["SelfMotivator"](./iterations/v4-SelfMotivator.md)|Simply encourage getting around the track in as few steps as possible|

|5|["Minimalist"](./iterations/v5-Minimalist.md)|How minimal can we go?|

|6|["re:Invent or Bust!"](./iterations/v6-reInventorBust.md)|Can I create a universal model?|

## Hyperparameter Optimizaiton

todo