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

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/bi1yav608uiv3dh234qgt0mdm
- Original: https://arxiv.org/abs/2410.03246

## Summary

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.