205b284b96
feat(hpc): parse missing dependencies dynamically from pyproject
2026-04-04 17:37:47 +02:00
Robin Meersman
62e11ce243
fix(PPOTrainer.py): bug fixes regarding jax.jit
2026-04-03 15:22:51 +02:00
Robin Meersman
a9302cfd4e
fix(PPOTrainer.py): cleaned up + bug fixes regarding misuse of variable/wrong returns
2026-04-03 14:54:57 +02:00
Robin Meersman
4396c9ac4b
feat(train.py, PPOTrainer.py): cleaned up training loop to specialized class
2026-04-03 14:23:09 +02:00
Robin Meersman
24da8948c5
fix(merge): fixed merge conflict after popping local changes back in from stash
2026-04-03 13:01:05 +02:00
Robin Meersman
1cb0e2d95b
fix(merge): fixed merge conflict
2026-04-03 12:58:40 +02:00
Cedric Mekeirle
4956e1593d
Merge pull request #6 from SELab-3-2026/chore/MLP_Designs
...
Semi Generic MLP library.
2026-04-03 12:55:37 +02:00
cedric
3104678f96
fix: uniform naming
2026-04-03 08:11:50 +00:00
cedric
1c4e40b5fb
fix: uniform naming of models accross code
2026-04-02 18:37:37 +00:00
cedric
79221372df
fix: uniform generic network naming
2026-04-02 18:18:10 +00:00
cedric
40c7e32344
feat: more generic naming for critic, since messager will use the same
2026-04-02 18:11:49 +00:00
cedric
729f122be4
fix: removed useless comment
2026-04-02 18:00:53 +00:00
cedric
95840b789b
fix: usage of field because flax wont allow mutable class object
2026-04-02 17:59:48 +00:00
cedric
9879fea9e2
fix: refactored rl folder into mlps
2026-04-02 17:50:44 +00:00
cedric
15ae86796f
feat: generic network
2026-04-02 17:38:46 +00:00
2263c97fe8
style: ruff format
2026-04-02 17:36:41 +00:00
cmekeirl
4e3eee8ac6
Basic centralized model
2026-04-02 17:36:41 +00:00
cmekeirl
1ad940ce02
Initial proposal for structure
2026-04-02 17:36:41 +00:00
Robin Meersman
ba59361f97
chore(main.py): deleted redundant main.py, feat(plot.py): added plot file to group all visualization related code for the experiments
2026-04-02 15:20:47 +02:00
Robin Meersman
97eaa5c06b
chore(train.py): moved from package to experiments directory
2026-04-02 15:13:27 +02:00
Robin Meersman
45587c5620
fix: losses --> episodic returns
2026-04-02 15:11:39 +02:00
Jona Reynaert
5329ae18ba
fix: removed deterministic flag
2026-04-02 10:36:18 +02:00
cedric
b2527e1a3c
fix: renamed MLPs with new names
2026-04-02 08:30:04 +00:00
Jona Reynaert
6db1129ca7
feat: implemented simulator
2026-04-02 10:26:52 +02:00
0e821cf251
docs: add HPC integration instructions
2026-04-01 19:34:47 +02:00
a774649ff0
test(hpc): add generic smoke test configuration
2026-04-01 19:34:47 +02:00
3c4f0b2ba3
fix(train): disable tqdm in batch mode to prevent log spam
2026-04-01 19:34:47 +02:00
e81708106d
ci(hpc): add slurm batch script for training
2026-04-01 19:34:47 +02:00
62e2adf97d
ci(hpc): add optimized installation script
2026-04-01 19:34:47 +02:00
d4529147cf
build(deps): relax python version constraint for HPC compatibility
2026-04-01 19:34:35 +02:00
RobinMeersman
f594cafead
Morphology/brittle star 2 arms ( #17 )
...
Provide the features to read in Environment (Morphology, arena, ...) config files in the JSON format. The example JSON file contains the config for a brittle star with 2 arms
2026-04-01 19:17:42 +02:00
ecdbe74df4
Merge pull request #9 from SELab-3-2026/chore/ppo
2026-04-01 18:11:59 +02:00
ff90101377
refactor(log): improved logging workflow
2026-04-01 16:01:12 +00:00
7e7c5bf27c
refactor: set wandb entity and simplify READMEs
2026-04-01 10:26:39 +02:00
3e992a3377
chore: update uv.lock
2026-04-01 07:59:26 +00:00
8347d81d70
test: add tests for YAML config loading
...
- test_config.py: covers load_yaml_config (happy path, missing file raises)
- Uses project-relative paths so tests run in any environment
2026-04-01 00:28:32 +02:00
e160a55d95
fix(train): integrate YAML config
2026-04-01 00:27:38 +02:00
2001a92e75
feat(config): add YAML config templates for dev, production and personal use
2026-04-01 00:27:00 +02:00
d27a617199
feat(experiment-logger): add config_utils module
...
- Add config_utils.py: load_yaml_config, save_yaml_config,
dataclass_from_dict, merge_config_with_cli, print_config
- Export new symbols from package __init__.py
2026-04-01 00:23:45 +02:00
cedric
f487d5725f
feat: extended reward function doc with efficiency idea
2026-03-31 22:20:19 +00:00
cedric
42e51e0653
fix: clarified seperate policy and value network part
2026-03-31 22:17:32 +00:00
cedric
209f9b6a3d
feat: MLP related design decisions doc
2026-03-31 22:09:37 +00:00
cedric
4e4ab629bd
fix: usage of uv for pre commit ruff format
2026-03-31 21:11:16 +00:00
8ec693f04c
fix(logging): improve JSON serialization and add wandb directory to gitignore
...
- Fix float32 serialization issue in unified logger metrics flushing
- Add jax.numpy import for proper type handling
- Add wandb/ directory to .gitignore to exclude temporary tracking files
- Tested wandb integration: metrics, artifacts, and local backup working correctly
2026-03-31 20:52:51 +00:00
dc3531071f
fix(devcontainer): update GPU runtime args for compatibility
...
Change from deprecated --gpus flag to --device for better
compatibility with newer Docker/CDI configurations.
2026-03-31 20:04:13 +00:00
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
f31436bccd
feat(config): add YAML configuration system
...
- Add default_ppo.yaml template for training configurations
- Create configs/README.md with usage documentation
- Enable per-researcher configuration without code changes
- Support YAML config files with CLI parameter overrides
- Document how to set personal WandB credentials safely
This allows researchers to maintain personal configs without
committing credentials to the repository.
2026-03-31 19:53:15 +00:00
4151d2307e
refactor(main): replace print with logging
2026-03-31 19:51:17 +00:00
b70cd1c27b
feat(train): integrate experiment_logger and replace print statements
...
- Replace direct WandB calls with experiment_logger.UnifiedLogger
- Replace all print() calls with proper logging framework
- Add automatic checkpoint saving every N iterations
- Configure root logger with proper format and level
- Maintain backward compatibility with TensorBoard writer
- Save final model with metadata using unified logger
2026-03-31 19:49:21 +00:00
bb0bb94f60
feat(config): add checkpoint frequency parameter
...
Add checkpoint_frequency to PPOArgs to enable periodic checkpoint
saving during training. Default: save every 100 iterations.
2026-03-31 19:49:12 +00:00
