Reproduce “Path Finding under Uncertainty through Probabilistic 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
David Tolpin, Brooks Paige, Jan Willem van de Meent, Frank Wood
The authors use probabilistic inference to learn stochastic depth-first-search policies for the Canadian Traveller Problem, where road states are initially unknown. They simulate trips, assign greater probability to policies producing shorter travel, and select a policy from the inferred distribution. In tested 20- and 50-node cases, travel cost improved 50–80% over a uniform policy, not specialized planners.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.