xlang-ai/text2reward

[ICLR 2024 Spotlight] Code for the paper "Text2Reward: Reward Shaping with Language Models for Reinforcement Learning"

Jupyter Notebook

Issues

About error
#3 opened 3 months ago by xiaolijz
2
How does this differ from Nvidia's Eureka generative rewards pipeline?
#2 opened a year ago by bdiu29
2
Require 2 python versions?
#1 opened a year ago by leo-liuzy
1