Article

Learning Action and Style Priors for Joint-Torque Control in Legged Robots

A study on deep reinforcement learning for legged robots proposes using latent actions learned from a small set of expert demonstrations as an inductive bias to help joint-level torque control policies explore more efficiently. This prior allows the agent to not be limited by the demonstration reward level and significantly improves performance on transfer tasks; when combined with style rewards for imitation, it can more closely match expert behavior. Related videos have been made public.

Part of the event: Proposing a motion and style prior method for legged locomotion learning

This page provides a summary and source link only.