DLR-RM/stable-baselines3

[Enhancement]: Wrong gains for weight initialization

Open

#1,559 opened on 2023年6月16日

GitHub で見る
 (2 comments) (0 reactions) (1 assignee)Python (6,550 stars) (1,407 forks)batch import
enhancementhelp wanted

説明

Enhancement

The recommended gains for the weight init depend on the used activation function, see torch docs. However, as for now the used gains are statically implemented and always the same in ActorCriticPolicies. See here.

I recommend making the gains dependent on the activation function used(, i.e. probably mainly ReLU and tanh).

If you agree with this, I would like to implement it myself and PR.

Thanks and a good day!

To Reproduce

--

Relevant log output / Error message

--

System Info

--

Checklist

  • I have checked that there is no similar issue in the repo
  • I have read the documentation
  • I have provided a minimal working example to reproduce the bug
  • I've used the markdown code blocks for both code and stack traces.

コントリビューターガイド

技術スタック
pythonpytorch
領域
machine learning
Issue 種別
feature
難度新しい貢献者にとっての実装難度です。1 は非常に小さな変更、5 は専門的な作業です。
3
推定時間経験ある貢献者が調査、実装、テスト、pull request 準備にかけるおおよその時間範囲です。
1-3 hours
活動状況Issue が今どれだけ取り組みやすいかを示します。新しい、活発、古い、ブロック中、またはメンテナー入力待ちなどです。
needs maintainer response
明確さ期待される変更、受け入れ条件、次の手順がどれだけ明確かを示します。
clear
前提条件
Basic knowledge of PyTorchUnderstanding of weight initializationFamiliarity with stable baselines3 codebase
初心者向け度初回貢献者にどれだけ取り組みやすいかを 1-100 で推定したスコアです。
60
調査方針
The issue is in stable baselines3/common/policies.py around line 589 where gains are statically set. The goal is to dynamically set gains based on activation function, following PyTorch's recommendations. The contributor should look at how activation functions are selected in the policy network and adjust the initialization accordingly. No linked PRs or assignee comments are visible.