Manipulation on DeepMind Manipulation tasks Modified Platform
96Average ReturnPIE-G
Evaluation Results
| Method | Links | |
|---|---|---|
| PIE-GZero-shot=true, Backbone=ResNet-18, Training Steps=500k, Action Repeat=22022.12 | 96 | |
| TLDAZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 89 | |
| SVEAZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 24 | |
| DrQ-v2Zero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 1.5 | |
| DrQZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 0.8 | |
| SACZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 0.5 |