Reinforcement Learning
stable-baselines3
Joblib
PyTorch
tabular-regression
xgboost
femtosecond-laser
hydrogel
GelMA
HAMA
laser-machining
SAC
materials-science
manufacturing
ml-intern
Instructions to use TWLab/femtosecond-laser-hydrogel-etching-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use TWLab/femtosecond-laser-hydrogel-etching-model with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="TWLab/femtosecond-laser-hydrogel-etching-model", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
| { | |
| "model": "XGBoost_NN_Ensemble+SAC_RL", | |
| "dataset_size": 12000, | |
| "features": [ | |
| "power_mW", | |
| "repetition_rate_kHz", | |
| "scan_speed_mm_s", | |
| "pulse_duration_fs", | |
| "wavelength_nm", | |
| "num_passes", | |
| "spot_diameter_um", | |
| "focal_offset_um", | |
| "water_content", | |
| "threshold_fluence_J_cm2", | |
| "absorption_depth_nm", | |
| "incubation_coefficient", | |
| "refractive_index", | |
| "youngs_modulus_kPa", | |
| "degree_of_methacrylation", | |
| "crosslink_density_mol_m3", | |
| "two_photon_cross_section_GM", | |
| "pulse_energy_uJ", | |
| "peak_fluence_J_cm2", | |
| "effective_pulses", | |
| "overlap_percent" | |
| ], | |
| "targets": [ | |
| "etch_depth_um", | |
| "etch_width_um", | |
| "surface_roughness_Sa_um", | |
| "aspect_ratio", | |
| "side_wall_angle_deg" | |
| ], | |
| "materials": [ | |
| "GelMA_5", | |
| "GelMA_7", | |
| "GelMA_10", | |
| "GelMA_15", | |
| "GelMA_20", | |
| "HAMA_1", | |
| "HAMA_2", | |
| "HAMA_3", | |
| "HAMA_5", | |
| "GH_6", | |
| "GH_9", | |
| "GH_13", | |
| "GH_20", | |
| "PEG", | |
| "PEGDA", | |
| "Collagen", | |
| "Alginate", | |
| "Silk" | |
| ], | |
| "surrogate": { | |
| "etch_depth_um": { | |
| "R2": 0.9745, | |
| "MAE": 1.0543 | |
| }, | |
| "etch_width_um": { | |
| "R2": 0.9845, | |
| "MAE": 2.3349 | |
| }, | |
| "surface_roughness_Sa_um": { | |
| "R2": 0.8409, | |
| "MAE": 28.1783 | |
| }, | |
| "aspect_ratio": { | |
| "R2": 0.7074, | |
| "MAE": 0.4861 | |
| }, | |
| "side_wall_angle_deg": { | |
| "R2": 0.9326, | |
| "MAE": 4.0329 | |
| } | |
| }, | |
| "rl": { | |
| "success": 0.0, | |
| "error": 37.015223483244576, | |
| "algo": "SAC", | |
| "gamma": 0.7 | |
| }, | |
| "refs": [ | |
| "TempoRL arxiv:2304.12187", | |
| "Recipe RL arxiv:2511.16297", | |
| "Petit JLMN 2025", | |
| "Biofabrication 2019 GelMA fs-laser", | |
| "ACS Appl Mater 2022 GelMA densification", | |
| "Bioactive Materials 2024 HAMA" | |
| ] | |
| } |