Reproduce “When Robots Outweigh Objects: How Inertia Mismatch Shapes Robot Policy Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Younghyo Park, Antonia Bronars, Pulkit Agrawal
The authors study how robot inertia affects learning to push a T-shaped object in simulation. They match controller response while varying robot and object masses, then compare reward-driven learning with imitation from demonstrations. Reward-driven policies succeed across the tested mass grid, while imitation works best with a light robot relative to the object; more data narrows but does not close the gap.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.