Assert that the VecNormalize wrapper handles the new truncations correctly · DLR-RM/stable-baselines3#1093 | Good First Issue

(2 评论) (0 反应) (0 负责人)Python (1,407 fork)batch import

help wanted

仓库指标

Star: (6,550 star)
PR 合并指标: (平均合并 11天 13小时) (30 天内合并 3 个 PR)

描述

I need to think more about that one, but my guess is that it should not matter much, the scaling is meant to avoid large values and to evolve with the agent performance. Still, we should double check that. Could you open an issue so we don't forget?

Originally posted by @araffin in https://github.com/DLR-RM/stable-baselines3/pull/780#discussion_r985247261

贡献者指南

研究方向: 研究 stable baselines3 中的 VecNormalize 实现，确保正确处理截断步骤（而非终止步骤）。查阅 PR #780 中的讨论，特别是 @araffin 的评论，并检查 vec normalize.py 中的相关源代码。寻找在非终止转换期间归一化更新的潜在问题，并验证缩放逻辑是否能在无偏差的情况下处理截断。
技术栈: python
领域: machine learning
议题类型: 测试
难度: 2
预计时间: 1-3 小时
活动状态: 活跃
清晰度: 基本清晰
前置要求: PythonPyTorchReinforcement learning
新手友好度: 70