BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-bd1de862c509c34de95c9a2655e48586@cmc.deusto.eus
DTSTART:20200909T103000Z
DTEND:20200909T113000Z
DTSTAMP:20251031T213500Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Modelling choices in model-based Reinforcement Learning
DESCRIPTION:Date: Wed. September 9, 2020\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg\nTitle: Modelling choices in model-based Reinforcement Learning\nSpeaker: Dr. Georgios Kontes\nAffiliation: Self-Learning Systems Group, Precise Positioning and Analytics Department, Fraunhofer Institute for Integrated Circuits IIS\nZoom meeting linkMeeting ID: 975 4039 5456 , PIN: 910962\nAbstract. Reinforcement Learning (RL) is an area of Machine Learning concerning with agents that take sequential decisions within an environment, aiming at solving a given problem. In the classical Reinforcement Learning paradigm the learning agent has no knowledge of the dynamics of the environment or labeled examples of correct actions, but instead must interact with the environment to design a policy (controller) that maximises future cumulative reward. Among the several different approaches within the RL ecosystem, model-based RL is one of the most sample-efficient, providing also some system safety guarantees. Here, a model of the system dynamics is learned using regression techniques and future actions are selected based on online planning algorithms that utilise the learned model. A core question here is which type of model to use: simpler models might not be expressive enough for complex problems or adequate for large datasets, while higher-capacity models tend to overfit to low-data regimes. Another important aspect is how to consider model uncertainty throughout planning, thus improving data efficiency during learning and safe operation during deployment. In this presentation, different variants from the RL literature for the model and the online planner will be presented.\n_\nDon’t miss out our Upcoming events!\n|| Subscribe to our FAU DCN-AvH newsletter\n
URL:https://cmc.deusto.eus/events-calendar/modelling-choices-in-model-based-reinforcement-learning/
CATEGORIES:FAU CAA Seminar,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/CAAseminar-default-wLogo-1.png
END:VEVENT
END:VCALENDAR