Reproduce “Recursive Self-Improvement of Exoskeleton Assistance Policies through Human-in-the-Loop Feedback” 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
Muyuan Ma, Shuo Jiang, Lijun Han, Xinpan Meng, Zhenghua Ma, Xiuze Xia, Houcheng Li, Long Cheng
The system lets an AI agent write and revise executable exoskeleton-assistance code using task and device information, measured performance, muscle activity, and participant feedback between operator-started trials. In a test with one participant, all five selected policies completed three tasks after one feedback round. However, ratings varied, and some assistance remained highly unsatisfactory.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.