thu-ml/tianshou

Reduce duplication between examples/atari/atari_network and examples/vizdoom/network

Open

#1,092 建立於 2024年4月3日

在 GitHub 查看
 (1 留言) (0 反應) (0 負責人)Python (7,121 star) (1,072 fork)batch import
good first issuerefactoring

描述

Also names could maybe be improved. Things there are called DQN and so, even though they're just nets, while there's an independent class called DQNPolicy, which has nothing to do with these classes

貢獻者指南

技術棧
pythonpytorch
領域
documentation
議題類型
refactor
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-3 hours
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
Familiarity with Python and PyTorchUnderstanding of neural network classes in RL
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
70
研究方向
The issue asks to reduce duplication between examples/atari/atari network and examples/vizdoom/network. Begin by comparing the two files to identify shared network architectures and common patterns. Look for ways to create a shared utility or base class, and update both files to use it. Additionally, consider renaming classes to align with the existing DQNPolicy class naming conventions. See comments on the issue for any guidance from maintainers.