Reproduce “MPBRS: Multi-Potential-Based Reward Shaping for Unified Reward Configuration in Humanoid Locomotion” 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
Van Chung Nguyen, Hung Manh La
The authors introduce multi-potential potential-based reward shaping (MPBRS) for humanoid locomotion, rewarding changes in posture-related signals rather than repeatedly rewarding desirable states. They use one reward structure and weight across nine simulated humanoids. In a Fourier N1 sensitivity test, at weight 500, MPBRS tracks velocity commands while direct reward shaping (DRS) stands still. This is not real-world evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.