Skip to content

Research - Try advanced network architectures (ResNet / SE blocks) #13

Description

@Codex-Crusader

Summary

Experiment with more advanced network backbones (e.g., Residual blocks, Squeeze-and-Excitation) for the policy/value heads.

Motivation

Stronger architectures may improve the model’s learning capacity and game strength.

Acceptance criteria / Definition of Done

  • Create a modular network construction (e.g., models/architectures.py) supporting at least:
    • Baseline small CNN (existing).
    • One ResNet-style variant (configurable via config.yaml).
  • Provide scripts / instructions to train or load the alternative architecture.
  • Report a short comparison (loss/validation metrics or small head-to-head) in docs/ showing any measurable differences or at least proving the architecture can train.

Implementation notes

  • Keep versions small and parameter-controlled so experiments remain tractable.
  • Ensure architecture choice is exposed in the config file (see config issue).

Complexity

Advanced — good for contributors with deep learning experience.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions