Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to nonfederal websites. Their policies may differ from this site.

Free, publiclyaccessible full text available January 1, 2023

Free, publiclyaccessible full text available December 1, 2022

We consider the distributed statistical learning problem in a highdimensional adversarial scenario. At each iteration, $m$ worker machines compute stochastic gradients and send them to a master machine. However, an $\alpha$fraction of $m$ worker machines, called Byzantine machines, may act adversarially and send faulty gradients. To guard against faulty information sharing, we develop a distributed robust learning algorithm based on Nesterov's dual averaging. This algorithms is provably robust against Byzantine machines whenever $\alpha\in[0, 1/2)$. For smooth convex functions, we show that running the proposed algorithm for $T$ iterations achieves a statistical error bound $\tilde{O}\big(1/\sqrt{mT}+\alpha/\sqrt{T}\big)$. This result holds for a largemore »

We study a distributed policy evaluation problem in which a group of agents with jointly observed states and private local actions and rewards collaborate to learn the value function of a given policy via local computation and communication. This problem arises in various largescale multiagent systems, including power grids, intelligent transportation systems, wireless sensor networks, and multiagent robotics. We develop and analyze a new distributed temporaldifference learning algorithm that minimizes the meansquare projected Bellman error. Our approach is based on a stochastic primaldual method and we improve the bestknown convergence rate from $O(1/\sqrt{T})$ to $O(1/T)$, where $T$ is the totalmore »

The 2D MultiAgent Path Finding (MAPF) problem aims at finding collisionfree paths for a number of agents, from a set of start locations to a set of goal locations in a known 2D environment. MAPF has been studied in theoretical computer science, robotics, and artificial intelligence over several decades, due to its importance for robot navigation. It is currently experiencing significant scientific progress due to its relevance for automated warehouses (such as those operated by Amazon) and other important application areas. In this paper, we demonstrate that some recently developed MAPF algorithms apply more broadly than currently believed in themore »

Free, publiclyaccessible full text available June 1, 2023

Free, publiclyaccessible full text available April 1, 2023