Reproduce “Reinforcement Learning Based Heterogeneous Task Allocation Under Spatio-Temporal Environmental Uncertainty for Multi-Robot Teams” 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 Lin, Yaxuan Li, Paul Szenher, Brendan Englot

The authors present a decentralized learned policy for assigning tasks to autonomous surface vehicles under conditions and unreliable communication. Each robot selects its next task locally, using gated observations and attention to account for robots and task needs. In simulations, it achieved the lowest makespan among tested methods, including with 100 robots and 400 tasks; this is not a sea trial.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.