DLR-RM/stable-baselines3

How do I export RecurrentPPO as an onnx model？

Open

#1,125 创建于 2022年10月17日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (6,550 star) (1,407 fork)batch import
help wantedquestion

描述

❓ Question

How do I export RecurrentPPO as an onnx model？

Checklist

  • I have checked that there is no similar issue in the repo
  • I have read the documentation
  • If code there is, it is minimal and working
  • If code there is, it is formatted using the markdown code blocks for both code and stack traces.

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
documentation
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
2
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
under 1 hour
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
无
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
70
研究方向
This issue asks how to export a RecurrentPPO model to ONNX format. The contributor should explore the existing ONNX export utilities in the stable baselines3 codebase (e.g., in sb3.common.onnx or similar) and test if they work with recurrent policies. If not, they may need to extend the export function to handle the recurrent state or propose a fix. Finally, they should update the documentation with a step by step guide.