BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:869@lincs.fr
DTSTART;TZID=Europe/Paris:20250117T140000
DTEND;TZID=Europe/Paris:20250117T170000
DTSTAMP:20250121T124908Z
URL:https://www.lincs.fr/events/exploiting-partial-system-knowledge-in-rei
 nforcement-learning-for-admission-control-and-electricity-storage-optimiza
 tion/
SUMMARY:Exploiting Partial System Knowledge in Reinforcement Learning for
 Admission Control and Electricity Storage Optimization
DESCRIPTION:This thesis exploits partial system knowledge to design more
 efficient reinforcement learning (RL) algorithms for three problems:
 admission control (1)\, electricity storage optimization (2)\, and the
 acceleration of bias function computation (3).\n\nFor (1)\, the system is
 modeled as an M/M/c/S queue with m job classes. We propose a model-based
 algorithm\, named UCRL-AC\, with a finite-time regret bound dominated by
 O(S\\log T + \\sqrt{mT \\log T})\, where T is the total running time.
 UCRL-AC exploits the queuing structure by learning the arrival
 rates.\n\nFor (2)\, we design an RL algorithm that minimizes energy and
 demand charges by controlling a battery. The knowledge of the battery
 dynamics allows an efficient offline exploration\, which enables fast
 training with minimal data. The algorithm is tested on real-world
 data.\n\nFor (3)\, we show that for a fixed policy\, the bias function
 computation can be accelerated through the knowledge of eigenvalues of the
 transition probability matrix.\n\n\nComposition du jury:\n\n 	Urtzi
 Ayesta\, IRIT (rapporteur)\n 	Giovanni Neglia\, Centre Inria d'Université
 Côte d'Azur (rapporteur)\n 	Johanne Cohen\, LISN - Université
 Paris-Saclay (examinatrice)\n 	Bruno Gaujal\, Inria Grenoble
 (examinateur)\n 	Alain Jean-Marie\, Inria Montpellier (examinateur)\n
 	Lorenzo Maggi\, NVIDIA (examinateur)\n 	Ana Buši?\, Inria Paris
 (directrice de thèse)\n 	Jiamin Zhu\, IFP Energies Nouvelles
 (co-encadrante de thèse)\n 	Tristan Charrier\, AMIAD (membre invité\,
 superviseur DGA)\n
CATEGORIES:PhD Defense
LOCATION:Inria Paris\, 48 rue Barrault\, Paris\, 75013\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=48 rue Barrault\, Paris\,
 75013\, France;X-APPLE-RADIUS=100;X-TITLE=Inria Paris:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR