Episode Details
Back to EpisodesLATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
Published 4 months, 2 weeks ago
Description
Introduces a three-stage pipeline that extracts a latent action space from low-quality human tennis demonstrations, then trains a high-level policy in simulation via reinforcement learning. Enables dynamic whole-body humanoid tennis play with back-and-forth volleys at human level.