https://github.com/maxreciprocate/offline

Offline RL experiments
https://github.com/maxreciprocate/offline

Last synced: 28 days ago
JSON representation

Offline RL experiments

• Host: GitHub
• URL: https://github.com/maxreciprocate/offline
• Owner: maxreciprocate
• License: mit
• Created: 2022-07-26T16:16:43.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2022-10-01T13:27:09.000Z (over 2 years ago)
• Last Synced: 2023-12-10T19:33:29.338Z (over 1 year ago)
• Language: Python
• Homepage:
• Size: 86.9 KB
• Stars: 12
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
Simplified implementation of [Implicit Language Q Learning (Snell et al. 2022)](https://sea-snell.github.io/ILQL_site/) ([official](https://github.com/Sea-Snell/Implicit-Language-Q-Learning/), [paper](https://arxiv.org/abs/2206.11871))

Evaluating on Graph Shortest Path task from [Decision Transformer (Lili Chen et al. 2021)](https://arxiv.org/abs/2106.01345):



where for each random graph, a transformer is trained to find optimal trajectories using only 1000 random walks.