REINVENT
GT4SD — Property-Conditioned Molecular Generation
SMILES-based reinforcement learning for de-novo molecule design.
Performance Metrics
| Metric | Value | Description |
|---|---|---|
| Published benchmarks | — | See the original REINVENT papers; GT4SD publishes no separate number |
Test Set
Model-specific
Notes
Not wired into Spectra: the GT4SD service registers this algorithm as a stub that returns an error naming a missing dependency. REINVENT is an established RL-based generator and its benchmarks are in the original papers; listed here because the upstream toolkit supports it.