Reproduce “EcoNet: Multiagent Planning and Control Of Household Energy Resources Using Active Inference” 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
John C. Boik, Kobus Esterhuysen, Jacqueline B. Hynes, Axel Constant, Ines Hipolito, Mahault Albarracin, Alex B. Kiefer, Karl Friston
EcoNet models a household energy management system with separate thermostat and battery agents that plan device actions around comfort, cost, and emissions preferences. Using active inference, the agents evaluate action sequences and share HVAC energy information. In a two-day synthetic simulation with underpowered HVAC, the daily average cumulative absolute temperature deviation was 22°C versus 64°C without HVAC; this is not real-home evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.