huru in the teleop-walking-benchmark: it walks fine, the arm motion is what stops it
hi; i ran an independent audit of the G1 ports in rhoyn/teleop-walking-benchmark with gaitkeeper, a tool i wrote that reads each port's adapter and runs the policy one change at a time; yours is one where the score undersells the policy
with its own arms it stands and tracks for the full 90 s on all 10 seeds; with the arms held still by the harness it still does 90 s; it lasts about 9 s once the harness moves the arms at random, and about 6 s under the full benchmark; so the low score there is about arm motion it wasn't trained under, not the walking; the port's values match the policy's own contract
per-run numbers and the stage-by-stage breakdown: https://dundysm.github.io/gaitkeeper/results/#huru
this is a behavioral finding in my runner (MuJoCo on a CPU, 10 seeds, each seed drawing the benchmark's own run), not a verdict on the policy; if anything looks off against what you see in training or on hardware, i'd like to know
the tool is open source if you want to run it on a newer checkpoint: https://github.com/dundysm/gaitkeeper