Accessibility-Based Clustering for Efficient Learning of Locomotion Skills
Chong Zhang,Wanming Yu,Zhibin Li,Chong Zhang,Wanming Yu,Zhibin Li
For model-free deep reinforcement learning of quadruped locomotion, the initialization of robot configurations is crucial for data efficiency and robustness. This work focuses on algorithmic improvements of data efficiency and robustness simultaneously through automatic discovery of initial states, which is achieved by our proposed K-Access algorithm based on accessibility metrics. Specifically, w...
