policy
crystal-rl
bshepp · PyTorch
or hover any field below to flag it
Overview
Name
crystal-rl
Author
bshepp
Framework
PyTorch
License
MIT
Skill type
navigation
Evidence level
untested
Task description
RL-driven discovery of semiconductor crystals with optimal effective mass. A PPO agent explores crystal structures guided by a two-phase surrogate model (MultiTaskMLP) trained on JARVIS-DFT and Materials Project data, with Quantum ESPRESSO DFT validation. 152-dim fingerprints, Docker-ready.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list crystal-rl yet.
Datasets that reference this policy
0No datasets reference crystal-rl yet.