Offline Context-conditioned Goal-oriented (CGO) Reinforcement Learning on Random Cells (large-play)
60.2Success RateCODA
Evaluation Results
| Method | Links | |
|---|---|---|
| CODA2024.08 | 60.2 | |
| Oracle Reward2024.08 | 59.8 | |
| PDS2024.08 | 48.1 | |
| Goal Prediction2024.08 | 44.3 |
Loading the SOTA2 catalog…