RLinf-ResNet10-pretrained

<div align="center"> <img src="logo.svg" alt="RLinf-logo" width="500"/> </div> <div align="center"> <a href="https://github.com/RLinf/RLinf"><img src="https://img.shields.io/badge/Github-blue"></a> <a href="https://rlinf.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/Documentation-Purple?color=8A2BE2&logo=readthedocs"></a> </div> <h1 align="center">RLinf: Reinforcement Learning Infrastructure for Agentic AI</h1>

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning. The 'inf' in RLinf stands for Infrastructure, highlighting its role as a robust backbone for next-generation training. It also stands for Infinite, symbolizing the system’s support for open-ended learning, continuous generalization, and limitless possibilities in intelligence development.

<div align="center"> <img src="overview.png" alt="RLinf-overview" width="600"/> </div>

Model Description

This repository provides a PyTorch ResNet-10 pretrained checkpoint, converted from the original JAX implementation released by the SeRL project.
The original JAX weights can be found here:
https://github.com/rail-berkeley/serl/releases/download/resnet10/resnet10_params.pkl

Within RLinf, this checkpoint is used as the pretrained CNN ResNet encoder for real-world embodied learning experiments.

How to Use

Please integrate the provided model with the RLinf codebase. To do so, modify the extra_config.pretrained_ckpt_path as the path for this model in the configuration file examples/embodiment/config/model/cnn_policy.yaml.

License

This code repository and the model weights are licensed under the MIT License.