Reproduce “Bridging Deep Reinforcement Learning and Motion Planning for Model-Free Navigation in Cluttered Environments” 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

Licheng Luo, Mingyu Cai

The authors introduce graph-based motion-planning guidance for model-free reinforcement learning in cluttered mazes. It computes cost-to-go across a connected roadmap and rewards progress while the policy learns unknown dynamics. In simulated tests with infeasible paths, it achieved near-100% success, while baselines failed, across quadrotor and vehicle models. This result applies to the tested settings, not real-world robots.

Summary by alphaXiv.

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