Zobrazeno 1 - 10
of 606
pro vyhledávání: '"Tang, Yujie"'
Autor:
Duan, Yingpeng, Tang, Yujie
This paper investigates distributed zeroth-order feedback optimization in multi-agent systems with coupled constraints, where each agent operates its local action vector and observes only zeroth-order information to minimize a global cost function su
Externí odkaz:
http://arxiv.org/abs/2410.12647
This paper investigates distributed zeroth-order optimization for smooth nonconvex problems. We propose a novel variance-reduced gradient estimator, which randomly renovates one orthogonal direction of the true gradient in each iteration while levera
Externí odkaz:
http://arxiv.org/abs/2409.19567
In everyday life, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a result, it becomes challenging for a robot to efficiently navigate to
Externí odkaz:
http://arxiv.org/abs/2409.18743
Autor:
Zhang, Silan, Tang, Yujie
We investigate accelerated zeroth-order algorithms for smooth composite convex optimization problems. While for unconstrained optimization, existing methods that merge 2-point zeroth-order gradient estimators with first-order frameworks usually lead
Externí odkaz:
http://arxiv.org/abs/2407.09190
Many optimal and robust control problems are nonconvex and potentially nonsmooth in their policy optimization forms. In Part II of this paper, we introduce a new and unified Extended Convex Lifting (ECL) framework to reveal hidden convexity in classi
Externí odkaz:
http://arxiv.org/abs/2406.04001
Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which reveals elegant nonconvex geometry in various benchmark problems, especia
Externí odkaz:
http://arxiv.org/abs/2312.15332
Distributed demand response is a typical distributed optimization problem that requires coordination among multiple agents to satisfy demand response requirements. However, existing distributed algorithms for this problem still face challenges such a
Externí odkaz:
http://arxiv.org/abs/2311.00372
This paper addresses the problem of pushing manipulation with nonholonomic mobile robots. Pushing is a fundamental skill that enables robots to move unwieldy objects that cannot be grasped. We propose a stable pushing method that maintains stiff cont
Externí odkaz:
http://arxiv.org/abs/2309.14295
Autor:
Tang, Yujie, Zheng, Yang
Direct policy search has achieved great empirical success in reinforcement learning. Recently, there has been increasing interest in studying its theoretical properties for continuous control, and fruitful results have been established for linear qua
Externí odkaz:
http://arxiv.org/abs/2304.00753
Edge caching is emerging as the most promising solution to reduce the content retrieval delay and relieve the huge burden on the backhaul links in the ultra-dense networks by proactive caching popular contents in the small base station (SBS). However
Externí odkaz:
http://arxiv.org/abs/2301.01141