Optimal Combination Policies For Adaptive Social Learning

Publications associées (26)

À propos
Confidentialité
Mentions légales

Graph Chatbot

Linear Speedup In Saddle-Point Escape For Decentralized Non-Convex Optimization

Ali H. Sayed, Stefan Vlaski

Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of agents) relative to no ...

IEEE2020

On the relation between transversal and longitudinal scaling in cities

João Vitor Meirelles de Miranda

Does the scaling relationship between population sizes of cities with urban metrics like economic output and infrastructure (transversal scaling) mirror the evolution of individual cities in time (longitudinal scaling)? The answer to this question has impo ...

2020

Generative adversarial training of product of policies for robust and adaptive movement primitives

Sylvain Calinon, Emmanuel Pignat, Hakan Girgin

In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which are often the kinem ...

2020

Sustainability as a Competitive Tool for the Brave? Or for the Best? A Behavioral Theory Perspective

Lorenzo Massa

Who invests in sustainability as a strategic choice? We adopt a behavioral theory perspective to explain the heterogeneity of sustainability-driven investments. Building on problemistic search and organizational inertia arguments, and contrary to resource- ...

SAGE PUBLICATIONS INC2020

Dynamic prediction-based relocation policies in one-way station-based carsharing systems with complete journey reservations

Nikolaos Geroliminis, Burak Boyaci, Martin Jean Marie Joseph Repoux, Mor Kaspi

In this paper, we study the operations of a one-way station-based carsharing system implementing a complete journey reservation policy. We consider the percentage of served demand as a primary performance measure and analyze the effect of several dynamic s ...

PERGAMON-ELSEVIER SCIENCE LTD2019

Distributed Value-Function Learning with Linear Convergence Rates

Ali H. Sayed, Kun Yuan, Lucas Cesar Eduardo Cassano

In this paper we develop a fully decentralized algorithm for policy evaluation with off-policy learning and linear function approximation. The proposed algorithm is of the variance reduced kind and achieves linear convergence with O(1) memory requirements. ...