
Guides training, evaluating and exporting reinforcement-learning robot policies for Isaac
- Open source
- 4K GitHub stars
- AI models and LLM tooling


Guides training, evaluating and exporting reinforcement-learning robot policies for Isaac

Grades or filters workflow HDF5 episodes by visual success using a vision model

Guides an agent through fine-tuning models on Microsoft Foundry with SFT, DPO or RFT

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Guides fine-tuning of NVIDIA Cosmos3 reasoning models with Cosmos Framework or Cosmos-RL

Fine-tunes HuggingFace vision, VLM and LLM models in an NVIDIA GPU container

Guides an agent through running, resuming and debugging NVIDIA FastGen training jobs

Chains AutoML tuning, a DEFT data-improvement loop and a final AutoML pass for PCB AOI

Plans and configures chained Nemotron customization steps like SFT, RL, and evaluation

Runs an iterative retrain-and-evaluate loop to improve NVIDIA TAO CLIP image-text

Prepares and validates a dataset and recipe for fine-tuning AnomalyGenNext LoRA weights

Fine-tunes and runs NVIDIA CLIP models for image-text retrieval and zero-shot
The closest alternatives to I4h workflow finetune are I4h workflow train rl, I4h workflow dataset annotate, Finetuning, Huggingface LLM trainer and Tao finetune cosmos reason.
Yes. I4h workflow train rl, I4h workflow dataset annotate, Finetuning have a free or open-source option.