Neural Reinforcement Learning Controllers for a Real Robot Application

By Roland Hafner, Martin A. Riedmiller. 2007

51 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Reinforcement Learning

In Robotics & Control

Citations in the corpus

Data-efficient Deep Reinforcement Learning for Dexterous Manipulation (2017, background): “In the last few years there has been a resurgence of interest in end-to-end training of neural networks for challenging control problems, and several algorithms, both value and policy focused have been developed and applied to challenging problems including continuous control, e.g. [22, 23, 6, 7,…”
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates (2016, background): “Although there has been considerable research on reinforcement learning with general-purpose neural networks for some time [13], [14], [15], [16], [17], such methods have only recently been developed to the point where they could be applied to continuous control of highdimensional systems, such as 7”
Learning contact-rich manipulation skills with guided policy search (2015, methodology): “Although a number of methods have been used to train neural network policies [17], [18], prior applications have required large amounts of training time and have been restricted either to lowdimensional systems or to high-level control.”
Reinforcement learning for robot soccer (2009, background): “For the complete setup and more information, see (Hafner and Riedmiller 2007).”
Reinforcement learning in feedback control (2011, methodology): “The NFQCA algorithm is a expansion of the Neural Fitted Q-Iteration (NFQ) algorithm (Riedmiller 2005; Hafner and Riedmiller 2007) that was developed especially within the context of reinforcement learning for feedback control applications.”
Learning to Drive a Real Car in 20 Minutes (2007, background): “Learning by interacting with the real system directly has an important advantage: the controller is tailored exactly to the behaviour of the real system at hand instead of a more or less exact model of it.”
Acquiring visual servoing reaching and grasping skills using neural reinforcement learning (2013, methodology): “However, advanced value-based methods such as Neural Fitted Q Iteration [15] work in a much more data-efficient manner and have proven to be usable in real-world systems rather than only simulated problems [16], [17].”