Similar Search Results

Directed principal component analysis

Kao, Yi-hao; Van Roy, Benjamin - In: Operations research 62 (2014) 4, pp. 957-972

Persistent link: https://www.econbiz.de/10010403095

Efficient reinforcement learning in deterministic systems with value function generalization

Wen, Zheng; Van Roy, Benjamin - In: Mathematics of operations research 42 (2017) 3, pp. 762-782

Persistent link: https://www.econbiz.de/10011742485

Control of diffusions via linear programming

Han, Jiarui; Van Roy, Benjamin - In: Stochastic programming : the state of the art ; in …, (pp. 329-353). 2011

Persistent link: https://www.econbiz.de/10008798646

Convergence of Min-Sum Message-Passing for Convex Optimization

Moallemi, Ciamac C. - 2012

We establish that the min-sum message-passing algorithm and its asynchronous variants converge for a large class of unconstrained convex optimization problems, generalizing existing results for pairwise quadratic optimization problems. The main sufficient condition is that of scaled diagonal...

Persistent link: https://www.econbiz.de/10013113813

Approximation benefits of policy gradient methods with aggregated states

Russo, Daniel - In: Management science : journal of the Institute for … 69 (2023) 11, pp. 6898-6911

Persistent link: https://www.econbiz.de/10014435438

A finite time analysis of temporal difference learning with linear function approximation

Bhandari, Jalaj; Russo, Daniel; Singal, Raghav - In: Operations research 69 (2021) 3, pp. 950-973

Persistent link: https://www.econbiz.de/10012546910

Global optimality guarantees for policy gradient methods

Bhandari, Jalaj; Russo, Daniel - In: Operations research 72 (2024) 5, pp. 1906-1927

Persistent link: https://www.econbiz.de/10015361758