Variance-Reduced Stochastic Learning by Networked Agents Under Random Reshuffling
Related publications (49)
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The dynamics of MEMS 3D fluidic self-assembly (FSA) was modeled using interactive software agents, i.e. by agent-based modeling (ABM). ABM enables realistic simulations of 3D FSA dynamics taking into account spatial parameters - hard to include in analytic ...
In cooperative multiagent systems, agents interact to solve tasks. Global dynamics of multiagent teams result from local agent interactions, and are complex and difficult to predict. Evolutionary computation has proven a promising approach to the design of ...
A recent method based on a specific power-law relationship between the matric potential head and the Boltzmann variable was presented by Prevedello et. al. (2008). Here, this relationship was generalized to a range of powers, and the solution extended to i ...
Despite the rigour and ability of game theory to cope with oligopolistic electric markets, it fails to model many existing behaviours in the real-world circumstances. The traditional models such as statistical extrapolation or econometrics are not capable ...
We address the problem of tomogram reconstruction in frequency-domain optical-coherence tomography. We propose a new technique for suppressing the autocorrelation artifacts that are commonly encountered with the conventional Fourier-transform-based approac ...
The solution obtained with the acoustical image sources method was shown to be the contribution of terms issued from a series development of the integral method (believed to be the exact solution). Missing terms in the geometrical method represent, among o ...
Over the past years, mobile agent technology has attracted considerable attention, and a significant body of literature has been published. To further develop mobile agent technology, reliability mechanisms such as fault tolerance and transaction support a ...
Our research focuses on the behavioral animation of virtual humans who are capable of taking actions by themselves. We deal more specifically with reinforcement learning methodologies, which integrate in an original way the RL agent and the autonomous virt ...
Multi agent system is a system consist of multiple interacting agents. These systems tend to select the best solution for their problems. They can be used in different tasks which are hard for an individual or even a complex system to do. One of the most c ...
Over the past years, mobile agent technology has attracted considerable attention, and a significant body of literature has been published. To further develop mobile agent technology, reliability mechanisms such as fault tolerance and transaction support a ...