tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity

Archived

This repository has been archived on 2026-08-15. You can view files and clone it, but you cannot make any changes to it's state, such as pushing and creating new issues, pull requests or comments.

Tibo De Peuter 7fe217de0f docs: update documentation for logging and configuration

- Add Quick Start guide with installation and configuration steps
- Document unified logging framework features
- Explain configuration management for multiple researchers
- Add project structure overview showing experiment_logger
- Update training examples with new patterns
- Add logging best practices to CONTRIBUTING.md

2026-03-31 19:53:45 +00:00

1.9 KiB

Raw Blame History

Brittle Star

Reinforcement learning research on brittle star locomotion using PPO.

Quick Start

Installation

Set up the environment using UV:

uv sync --frozen

Configuration

Copy the default configuration:

cp configs/default_ppo.yaml configs/my_experiment.yaml

Edit configs/my_experiment.yaml to set your WandB credentials:

track: true  # Enable WandB logging
wandb_entity: "your-wandb-username"  # Replace with your username/team
wandb_project_name: "PPO-Modularity"

(Optional) Login to WandB:
```
uv run wandb login
```

Training

Run training with your configuration:

uv run python src/train.py

Or use a custom config file:

uv run python src/train.py --config configs/my_experiment.yaml

Override specific parameters:

uv run python src/train.py --learning-rate 0.001 --num-envs 32 --track

Logging

The training script uses a unified logging framework that:

Logs to WandB (when enabled)
Saves metrics to local disk (JSON files in runs/)
Displays progress in stdout

All experiment data is preserved locally, even if WandB is unavailable.

Project Structure

src/brittle_star_project/  # Core library (reusable components)
├── logging/               # Unified logging framework
├── environment/           # Environment wrappers
├── rl/                    # RL algorithms and models
└── dataclasses/          # Configuration dataclasses

configs/                   # Training configurations
runs/                      # Training outputs (checkpoints, metrics)

For Researchers

Important: Do not commit your personal WandB credentials to the repository. Instead, create your own config file (e.g., configs/yourname.yaml) and add it to .gitignore if needed.

See configs/README.md for more details on configuration management.

1.9 KiB Raw Blame History