1. Simulates a quadruped robot in MuJoCo. 2. Trains an actor-critic neural network with Proximal Policy Optimization. 3. Saves the best checkpoint and records a short video.
Abstract: Service robots usually need to navigate in a complex indoor environment, and sometimes robots need to perform target search tasks autonomously without a prebuilt map. The existing navigation ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果