Reproduce “Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts” 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
Daniel Garces, Sara Castro, Adrian Haimovich, Byron Crowe, Stephanie Gil
The proposed adaptive rollout policy uses sampled future requests to evaluate assignments for observed tasks, adjusts prediction weights using recent forecast errors, and reconsiders eligible unstarted assignments. In held-out high-demand simulations using nursing-task requests, it had the lowest median mean and 95th-percentile wait times, with reductions of approximately 5% and 10%, respectively. These results do not establish performance beyond simulation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.