artificial intelligence Hierarchical Learning for Modular Robots HRL methods allow the robot to learn to perform a certain task in the level of macro-actions, a set of individual actions reducing the search space. This makes the learning process faster and more scalable, and allows the robot to generalize across unseen tasks or environments.
artificial intelligence Deep Reinforcement Learning Methods for Modular Robots A framework with Gazebo and ROS that simplifies the process of building modular robots and their corresponding tools. It includes baseline implementations for the most common DRL techniques dealing with policy iteration methods.
