Reproduce “Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped” 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
Jagannath Prasad Sahoo, Saurabh Kumar, Surya Prakash S.K., Samiran Datta, Abhay Dwivedi, Amit Shukla
The authors present a jointly trained hierarchical controller for bipedal obstacle avoidance in simulation. A high-level policy uses obstacle motion and a time-to-collision reward to choose body-velocity commands; a low-level policy converts them into joint targets. In 100 dynamic-obstacle trials, it reached the goal in 88%, versus 68% for SAC+A*, with a shared gait, in this simulated setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.