Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 3
Dynamic raw material ordering under demand uncertainty: a Markov chain–newsvendor approach
Y. Zhao, Z. Ma, Y. Wang, X. Su
Izvirni znanstveni članek
Oznake: upravljanje dobavnih verig;upravljanje zalog;naročanje surovin;napoved povpraševanja;Markovska veriga;model prodajalca časopisov;sistem za podporo odločanju;supply chain management;inventory management;ordering of raw materials;demand forecast;Markov chain;newsvendor model;decision support system;
Raw material ordering under demand uncertainty is often hindered by inaccurate forecasts, resulting in excess inventory, stockouts, and increased operating costs. Traditional Newsvendor models typically assume static demand distributions and therefore have limited ability to capture dynamic changes ...
Leto: 2026 Vir: Digitalna knjižnica Univerze v Mariboru (DKUM)
Active Learning for Reward Estimation in Inverse Reinforcement Learning
Francisco S. Melo
Video in druga učna gradiva
Oznake: computer science;machine learning;active learning
Inverse reinforcement learning addresses the general problem of recovering a reward function from samples of a policy provided by an expert/demonstrator. In this paper, we introduce active learning for inverse reinforcement learning. We propose an algorithm that allows the agent to query the demonst ...
Leto: 2009 Vir: videolectures.net
An Analysis of Reinforcement Learning with Function Approximation
Francisco S. Melo
Video in druga učna gradiva
Oznake: computer science;machine learning;reinforcement learning
We address the problem of computing the optimal Q-function in Markov decision problems with infinite state-space. We analyze the convergence properties of several variations of Q-learning when combined with function approximation, extending the analysis of TD-learning in (Tsitsilis and Van Roy, 1996 ...
Leto: 2008 Vir: videolectures.net
Št. zadetkov: 3
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: