Manipulation on DeepMind Manipulation tasks Modified Arm
122Average ReturnPIE-G
Evaluation results
| Method | Links | |
|---|---|---|
| PIE-GZero-shot=true, Backbone=ResNet-18, Training Steps=500k, Action Repeat=22022.12 | 122 | |
| DrQZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 68 | |
| TLDAZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 55 | |
| DrQ-v2Zero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 29 | |
| SVEAZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 21 | |
| SACZero-shot=true, Training Steps=500k, Action Repeat=22022.12 | 0.3 |