Patch Policy (CLS versus Dense)· Iteration 1
EnvironmentPlace spray bottles upright, nozzle forward (bimanual handover)
- Episodes
- CLS token 30 Patch Policy (CLS versus Dense) 30
- Total duration
- CLS token 33:46 Patch Policy (CLS versus Dense) 36:45
- Mean duration
- CLS token 67.5 s Patch Policy (CLS versus Dense) 73.5 s
- Success
- CLS token 23% Patch Policy (CLS versus Dense) 43%
- Manipulation density
- CLS token Share of time manipulating, five definitionsJoints moving99.9%End-effector moving99.0%Gripper engaged73.2%Contact force > 5 N69.8%Gripper engaged or in contact91.2% Patch Policy (CLS versus Dense) Share of time manipulating, five definitionsJoints moving99.8%End-effector moving97.4%Gripper engaged74.6%Contact force > 5 N72.0%Gripper engaged or in contact94.6%
- SPARC smoothness
- CLS token Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Patch Policy (CLS versus Dense) Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015.
Episode
Held-out benchmark environment
0:001:43