Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning

no code implementations • 11 Mar 2021 • Guillaume Bellegarda, Yiyu Chen, Zhuochen Liu, Quan Nguyen

Policies can be learned in only a few million time steps, even for challenging tasks of running over rough terrain with loads of over 100% of the nominal quadruped mass.

reinforcement-learning Reinforcement Learning (RL) +1