Print Email Facebook Twitter Decentralized Reinforcement Learning of robot behaviors Title Decentralized Reinforcement Learning of robot behaviors Author Leottau, David L. (Universidad de Santiago de Chile) Ruiz-del-Solar, Javier (Universidad de Santiago de Chile) Babuska, R. (TU Delft Learning & Autonomous Control; Czech Technical University) Date 2018 Abstract A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned in parallel by individual agents working toward a common goal. In addition to proposing this methodology, three specific multi agent DRL approaches are considered: DRL-Independent, DRL Cooperative-Adaptive (CA), and DRL-Lenient. These approaches are validated and analyzed with an extensive empirical study using four different problems: 3D Mountain Car, SCARA Real-Time Trajectory Generation, Ball-Dribbling in humanoid soccer robotics, and Ball-Pushing using differential drive robots. The experimental validation provides evidence that DRL implementations show better performances and faster learning times than their centralized counterparts, while using less computational resources. DRL-Lenient and DRL-CA algorithms achieve the best final performances for the four tested problems, outperforming their DRL-Independent counterparts. Furthermore, the benefits of the DRL-Lenient and DRL-CA are more noticeable when the problem complexity increases and the centralized scheme becomes intractable given the available computational resources and training time. Subject Autonomous robotsDecentralized controlDistributed artificial intelligenceMulti-agent systemsReinforcement learning To reference this document use: http://resolver.tudelft.nl/uuid:ca8f4bdd-643f-4d3f-83af-52195921fec6 DOI https://doi.org/10.1016/j.artint.2017.12.001 Embargo date 2019-12-22 ISSN 0004-3702 Source Artificial Intelligence, 256, 130-159 Bibliographical note Accepted Author Manuscript Part of collection Institutional Repository Document type journal article Rights © 2018 David L. Leottau, Javier Ruiz-del-Solar, R. Babuska Files PDF MAS_DRL.pdf 6.87 MB Close viewer /islandora/object/uuid:ca8f4bdd-643f-4d3f-83af-52195921fec6/datastream/OBJ/view