Prioritized Experience Replay for DQN

Description

Contributor guide

Tech stack

pythonpytorch

Domain

machine learning

Issue type

feature

DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.

3

Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.

3-5 days

Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.

active

ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.

needs investigation

Prerequisites

Familiarity with DQNPyTorch basicsStable Baselines3 codebase

Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.

30

Research direction

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.