Reproduce “Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning” 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
Xi Chen, Julien Cumin, Fano Ramparany, Dominique Vaufreydaz
The authors introduce LLM+BC for assigning ambient sensor events to residents in shared homes. The policy uses prior resident-specific event histories and behavior cloning to learn assignments from annotated examples. On MuRAL, it achieves Acc 0.773 and RCE 0.261, compared with LAHAR’s 0.616 and 0.571. Transfer remains asymmetric, and concurrent-event resident-count estimates are correct for only about 41% of cases.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.