Molecular Property Optimization on easy synth druglike
0.99Normalized RewardRL
Evaluation Results
| Method | Links | |
|---|---|---|
| RLRL training budget=20002026.04 | 0.99 | |
| π(·|y*)2026.04 | 0.86 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.04 | 0.62 | |
| RLRL training budget=10002026.04 | 0.6 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.04 | 0.58 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.04 | 0.56 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.04 | 0.48 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.04 | 0.4 | |
| RLRL training budget=5002026.04 | 0.4 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.04 | 0.24 |