منابع مشابه
Optimal Learning with Q - Aggregation
We consider a general supervised learning problem with strongly convex and Lipschitz loss and study the problem of model selection aggregation. In particular, given a finite dictionary functions (learners) together with the prior, we generalize the results obtained by Dai, Rigollet and Zhang [Ann. Statist. 40 (2012) 1878–1905] for Gaussian regression with squared loss and fixed design to this l...
متن کاملDeviation Optimal Learning using Greedy Q-aggregation
Given a finite family of functions, the goal of model selection aggregation is to construct a procedure that mimics the function from this family that is the closest to an unknown regression function. More precisely, we consider a general regression model with fixed design and measure the distance between functions by the mean squared error at the design points. While procedures based on expone...
متن کاملEvaluating project’s completion time with Q-learning
Nowadays project management is a key component in introductory operations management. The educators and the researchers in these areas advocate representing a project as a network and applying the solution approaches for network models to them to assist project managers to monitor their completion. In this paper, we evaluated project’s completion time utilizing the Q-learning algorithm. So the ...
متن کاملEvaluating project’s completion time with Q-learning
Nowadays project management is a key component in introductory operations management. The educators and the researchers in these areas advocate representing a project as a network and applying the solution approaches for network models to them to assist project managers to monitor their completion. In this paper, we evaluated project’s completion time utilizing the Q-learning algorithm. So the ...
متن کاملWhen the Best Move Isn't Optimal: Q-learning with Exploration
The most popular delayed reinforcement learning technique, Q-learning (Watkins 1989)) estimates the future reward expected from executing each action in every state. If these estimates are correct, then an agent can use them to select the action with maximal expected future reward in each state, and thus perform optimally. Watkins has proved that Q-learning produces an optimal policy (the funct...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Statistics
سال: 2014
ISSN: 0090-5364
DOI: 10.1214/13-aos1190