thu-ml/tianshou

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

Open

#1,092 opened on Apr 3, 2024

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (7,121 stars) (1,072 forks)batch import
good first issuerefactoring

Description

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

Contributor guide

Tech stack
pythonpytorch
Domain
documentation
Issue type
refactor
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.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Familiarity with Python and PyTorchUnderstanding of neural network classes in RL
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
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.