RLinf: Reinforcement Learning Infrastructure for Agentic AI
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.
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.