xlang-ai/text2reward

[ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

29
/ 100
Experimental

This tool helps AI researchers and reinforcement learning practitioners quickly define and refine reward functions for their agents. It takes natural language descriptions of desired agent behaviors and automatically generates executable reward code. This allows for faster experimentation and iteration on complex robotic tasks or simulated environments without extensive manual coding of reward signals.

201 stars. No commits in the last 6 months.

Use this if you are developing reinforcement learning agents and want to leverage language models to automatically generate and shape reward functions from text descriptions.

Not ideal if you are a beginner in reinforcement learning or not comfortable with command-line operations and basic Python environment setup.

reinforcement-learning-research robotics-simulation AI-agent-development reward-engineering natural-language-for-AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

201

Forks

12

Language

Jupyter Notebook

License

Last pushed

Dec 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/xlang-ai/text2reward"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.