tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
Archived
1
Fork 0
Code Issues Releases Activity
This repository has been archived on 2026-08-15.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.
2026SEL3-project-Brittle_St.../configs
History
Robin Meersman 6114e36e27 feat(PPOTrainer): decentralized message passing babyyyy
2026-05-02 21:50:42 +02:00
..
architecture feat(PPOTrainer): decentralized message passing babyyyy 2026-05-02 21:50:42 +02:00
arena feat: add modular configuration files 2026-04-14 22:43:28 +02:00
environment feat(PPOTrainer): decentralized message passing babyyyy 2026-05-02 21:50:42 +02:00
experiment feat(PPOTrainer): decentralized message passing babyyyy 2026-05-02 21:50:42 +02:00
logging fix: custom reward function dependent on env reward + extensions 2026-04-17 14:23:57 +02:00
morphology fix(PR#41): applied comments for PR #41 review 2026-04-18 11:07:01 +02:00
ppo feat(PPOTrainer): decentralized message passing babyyyy 2026-05-02 21:50:42 +02:00
simulation feat: adapted simulate to trained config 2026-04-22 18:47:35 +02:00
main_config.yaml feat: simulation config 2026-04-15 19:39:39 +02:00
README.md fix: rediect logs 2026-04-15 18:44:37 +02:00

README.md

Brittle Star Configuration System

This project uses Hydra for a modular, hierarchical, and strictly-typed configuration system.

Core Concepts

  1. Composition over Inheritance: Instead of one giant config file, the configuration is composed of small, domain-specific modules (PPO settings, architecture, morphology, etc.).
  2. Strict Typing: Every configuration is validated against a Python dataclass schema (ConfigStore). Misspelled keys throw a ConfigAttributeError immediately.
  3. CLI Swapping: You can swap entire modules or override individual values from the command line without touching code.

Directory Structure

  • main_config.yaml: The root entry point defining the default composition.
  • experiment/: High-level experiment settings (seed, device).
  • logging/: WandB and checkpointing configuration.
  • ppo/: PPO training hyperparameters.
  • architecture/: Polymorphic network architectures (centralized vs. decentralized).
  • morphology/: Physical robot definitions (number of segments, amputations).
  • arena/: Environment physics and visual settings.
  • environment/: Task-specific settings (Directed Locomotion, Light Escape).

Common Commands

Local Debugging

Run a quick test with minimal iterations:

python scripts/train.py experiment=dev_test ppo=fast

Swapping Architectures or Morphologies

Test a decentralized controller on a 3-arm robot:

python scripts/train.py architecture=decentralized morphology=3_arms

HPC Production

Run stable PPO with WandB enabled (HPC submission scripts handle the hydra.run.dir redirection):

python scripts/train.py ppo=stable logging=wandb_enabled

Dry-Run Validation

Check if your configuration is valid without starting the simulation:

python scripts/train.py --cfg job

Developer Notes

  • Adding a new group: Create a subdirectory in configs/ and register the new dataclass in src/brittle_star_project/configs/register_configs.py.
  • Typo Catching: If you see a ConfigAttributeError, check for typos in your YAML keys or CLI overrides.
  • Output Redirection: We use experiment.base_run_dir to configure where logs and models are stored (defaults to runs/).
    • To change it locally: python scripts/train.py experiment.base_run_dir=/path/to/custom/dir
    • On HPC, ensure this points to a fast scratch storage.