Reinforcement Learning on Box-Pushing dense
20Environment Steps (M)GTrXL policy
Evaluation results
| Method | Links | |
|---|---|---|
| GTrXL policy2025.03 | 20 | |
| SAC2025.03 | 15 | |
| CrossQ2025.03 | 10 | |
| T-SAC2025.03 | 4 | |
| TOP-ERL2025.03 | 2 |
| Method | Links | |
|---|---|---|
| GTrXL policy2025.03 | 20 | |
| SAC2025.03 | 15 | |
| CrossQ2025.03 | 10 | |
| T-SAC2025.03 | 4 | |
| TOP-ERL2025.03 | 2 |