Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 5
Divertor conceptual design of the European Volumetric Neutron Source
Jean Boscary, Pietro Vinoni, Domenico Marzullo, Aljaž Čufar, Christian Bachmann, R. Neu
Izvirni znanstveni članek
Oznake: fuzijski reaktorji;fusion reactors;volumetric neutron source;plasma facing component;divertor;
The goal of the European plasma Volumetric Neutron Source (VNS), which is a 14 MeV n-source, is to test and validate technological solutions of breeding blankets in an environment representative of a future fusion power plant such as DEMO. One of the assessed magnetic configurations is a tokamak dev ...
Leto: 2025 Vir: Institut Jožef Stefan (IJS)
Prediction by random-walk perturbation
Gergely Neu
Video in druga učna gradiva
Oznake: computer science;machine learning
We propose a version of the follow-the-perturbed-leader online prediction algorithm in which the cumulative losses are perturbed by independent symmetric random walks. The forecaster is shown to achieve an expected regret of the optimal order O(√nlogN) where n is the time horizon and N is the number ...
Leto: 2013 Vir: videolectures.net
Online Learning in Non-Stationary Markov Decision Processes
Gergely Neu
Video in druga učna gradiva
Oznake: computer science;machine learning;on-line learning
We consider online learning in Markov decision processes with adversarial reward functions. Depending on the information available to the decision maker, we analyze two scenarios: in one setup the stochastic dynamics are known but only the rewards actually received can be observed, while, in the oth ...
Leto: 2013 Vir: videolectures.net
Online Markov Decision Processes under Bandit Feedback
Gergely Neu
Video in druga učna gradiva
Oznake: computer science;machine learning;markov processes
We consider online learning in finite stochastic Markovian environments where in each time step a new reward function is chosen by an oblivious adversary. The goal of the learning agent is to compete with the best stationary policy in terms of the total reward received. In each time step the agent o ...
Leto: 2010 Vir: videolectures.net
First-order regret bounds for combinatorial semi-bandits
Gergely Neu
Video in druga učna gradiva
Oznake: computer science;machine learning;on-line learning;reinforcement learning;semi-supervised learning;active learning;computational learning theory
We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses a ...
Leto: 2015 Vir: videolectures.net
Št. zadetkov: 5
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: