Print Email Facebook Twitter Learning state representation for deep actor-critic control Title Learning state representation for deep actor-critic control Author Munk, J. Kober, J. (TU Delft OLD Intelligent Control & Robotics) Babuska, R. (TU Delft OLD Intelligent Control & Robotics) Contributor Bullo, Francesco (editor) Prieur, Christophe (editor) Giua, Alessandro (editor) Date 2016 Abstract Deep Neural Networks (DNNs) can be used as function approximators in Reinforcement Learning (RL). One advantage of DNNs is that they can cope with large input dimensions. Instead of relying on feature engineering to lower the input dimension, DNNs can extract the features from raw observations. The drawback of this end-to-end learning is that it usually requires a large amount of data, which for real-world control applications is not always available. In this paper, a new algorithm, Model Learning Deep Deterministic Policy Gradient (ML-DDPG), is proposed that combines RL with state representation learning, i.e., learning a mapping from an input vector to a state before solving the RL task. The ML-DDPG algorithm uses a concept we call predictive priors to learn a model network which is subsequently used to pre-train the first layer of the actor and critic networks. Simulation results show that the ML-DDPG can learn reasonable continuous control policies from high-dimensional observations that contain also task-irrelevant information. Furthermore, in some cases, this approach significantly improves the final performance in comparison to end-to-end learning. Subject Approximation algorithmsRobot sensing systemsAlgorithm design and analysisPrediction algorithmsLearning (artificial intelligence)Feature extraction To reference this document use: http://resolver.tudelft.nl/uuid:1830de68-f008-471f-898f-0665c2a907d2 DOI https://doi.org/10.1109/CDC.2016.7798980 Publisher IEEE, Piscataway, NJ, USA ISBN 978-1-5090-1837-6 Source Proceedings 2016 IEEE 55th Conference on Decision and Control (CDC) Event 55th IEEE Conference on Decision and Control, CDC 2016, 2016-12-12 → 2016-12-14, Las Vegas, United States Bibliographical note Accepted Author Manuscript Part of collection Institutional Repository Document type conference paper Rights © 2016 J. Munk, J. Kober, R. Babuska Files PDF Jelle_Munk_CDC2016_author ... ersion.pdf 465.93 KB Close viewer /islandora/object/uuid:1830de68-f008-471f-898f-0665c2a907d2/datastream/OBJ/view