DLR-RM/stable-baselines3

Prioritized Experience Replay for DQN

Open

#1,242 建立於 2022年12月26日

在 GitHub 查看
 (10 留言) (0 反應) (0 負責人)Python (6,550 star) (1,407 fork)batch import
enhancementhelp wanted

描述

🚀 Feature

Prioritized Experience Replay for DQN

Motivation

No response

Pitch

No response

Alternatives

No response

Additional context

No response

Checklist

  • I have checked that there is no similar issue in the repo

貢獻者指南

技術棧
pythonpytorch
領域
machine learning
議題類型
feature
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。
3-5 days
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。
active
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
needs investigation
前置要求
Familiarity with DQNPyTorch basicsStable Baselines3 codebase
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。
30
研究方向
The issue requests implementing Prioritized Experience Replay (PER) for DQN, as introduced in the paper by Schaul et al. (2015). Start by examining the existing DQN implementation in stable baselines3, located in `stable baselines3/dqn/`. The PER logic should modify the replay buffer to sample transitions with probability proportional to TD error, and adjust the loss accordingly. Reference other implementations like the one in `openai/baselines` or `rl adventure` for guidance. Engaging with the issue comments may reveal community suggestions or potential design decisions.