Endowing robots with human-like abilities to perform motor skills in a smooth and natural way is one of the important goals of robotics. A promising way to achieve this is by creating robots that can learn new skills by themselves, similarly to humans. However, acquiring new motor skills is not simple and involves various forms of learning. Over the years, the approaches for teaching new skill to robots have evolved significantly, and currently, there are three well-established types of approaches: direct programming, imitation learning and reinforcement learning.
In robotics, the ultimate goal of reinforcement learning is to endow robots with the ability to learn, improve, adapt and reproduce tasks with dynamically changing constraints based on exploration and autonomous learning. We give a summary of the state-of-the-art of reinforcement learning in the context of robotics, in terms of both algorithms and policy representations. Three recent examples for the application of reinforcement learning to real-world robots are described: a pancake flipping task, a bipedal walking energy minimization task and an archery-based aiming task.
Sources:
