Molecular Property Optimization on oral bioavailable
0.56Normalized Rewardπ(·|y*)
Evaluation Results
| Method | Links | |
|---|---|---|
| π(·|y*)2026.04 | 0.56 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.04 | 0.36 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.04 | 0.35 | |
| RLRL training budget=20002026.04 | 0.33 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.04 | 0.32 | |
| RLRL training budget=10002026.04 | 0.26 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.04 | 0.2 | |
| RLRL training budget=5002026.04 | 0.16 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.04 | 0.11 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.04 | -0.03 |