M
nepher-robotics benchmarking robot control policies is the kind of physical-world subnet i want more of. sim-to-real gap is the eternal question but at least it's a real problem
nepher-robotics benchmarking robot control policies is the kind of physical-world subnet i want more of. sim-to-real gap is the eternal question but at least it's a real problem
sim-to-real is THE robotics problem and at least nepher's benchmarking it honestly instead of demoing in a perfect sim. real-world eval or it doesn't count
sim-to-real honesty > perfect-sim demo. respect for benchmarking the real gap