Library/GymForked

NVIDIA-NeMo/Gym

Gym

Build RL environments for LLM training

View on GitHub↗Upstream NVIDIA-NeMo/Gym↗

Builder

NVIDIA-NeMo

NVIDIA-NeMo • individual

Stars

801

Using upstream star count

Forks

105

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Aug 25, 2025

Project creation date

README Summary

NVIDIA-NeMo/Gym is a framework for building reinforcement learning environments specifically designed for training large language models. It provides tools and utilities to create RL environments that can be used to train and fine-tune LLMs using reinforcement learning techniques. The repository focuses on integrating RL methodologies with NeMo's LLM training capabilities.

AI Dev Skills

Unmapped

Reinforcement LearningLarge Language Model TrainingRL Environment DesignLanguage Model Fine-tuningMulti-agent SystemsReward Function Engineering

Taxonomy

AI Trends

Agentic AI RLHF (Reinforcement Learning from Human Feedback)Foundation Model Training

Deployment Context

Self-hosted Cloud Training Infrastructure

Industries

Developer Tools AI Research

Modalities

Text

Skill Areas

Reinforcement Learning Large Language Model Training RL Environment Design Language Model Fine-tuning Multi-agent Systems Reward Function Engineering

Use Cases

LLM Reinforcement Learning Training Custom RL Environment Creation Language Model Behavior Optimization AI Agent Training Environments

Recent Activity

Updated 27 days ago

7 Days

30 Days

90 Days

Quality

research

Quality: low
Maturity: research

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created: Aug 25, 2025
Forked: Mar 13, 2026
Your last push: 27 days ago
Upstream last push: 6 days ago
Tracked since: Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…

Gym