Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Zhang, Xuezhou"'
Autor:
Chen, Mingyu, Zhang, Xuezhou
This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping \underline{B}oun
Externí odkaz:
http://arxiv.org/abs/2403.00930
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the loss functi
Externí odkaz:
http://arxiv.org/abs/2311.07876
Multi-level optimization has gained increasing attention in recent years, as it provides a powerful framework for solving complex optimization problems that arise in many fields, such as meta-learning, multi-player games, reinforcement learning, and
Externí odkaz:
http://arxiv.org/abs/2310.06217
Autor:
Chen, Mingyu, Zhang, Xuezhou
We consider the Adversarial Multi-Armed Bandits (MAB) problem with unbounded losses, where the algorithms have no prior knowledge on the sizes of the losses. We present UMAB-NN and UMAB-G, two algorithms for non-negative and general unbounded loss re
Externí odkaz:
http://arxiv.org/abs/2310.01756
In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for
Externí odkaz:
http://arxiv.org/abs/2306.12356
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hi
Externí odkaz:
http://arxiv.org/abs/2211.10530
We study multi-agent general-sum Markov games with nonlinear function approximation. We focus on low-rank Markov games whose transition matrix admits a hidden low-rank structure on top of an unknown non-linear representation. The goal is to design an
Externí odkaz:
http://arxiv.org/abs/2210.16976
Autor:
Zhang, Xuezhou1 (AUTHOR), Hong, Baoan1 (AUTHOR), Li, Hongwei2 (AUTHOR), Zhao, Jiahui1 (AUTHOR), Li, Mingchuan1 (AUTHOR), Wei, Dechao1 (AUTHOR), Wang, Yongxing1 (AUTHOR), Zhang, Ning1 (AUTHOR) Azurology_zn@126.com
Publikováno v:
BMC Cancer. 6/19/2024, Vol. 24 Issue 1, p1-13. 13p.
Autor:
Huang, Kaixuan, Wu, Yu, Zhang, Xuezhou, Tu, Shenyinying, Wu, Qingyun, Wang, Mengdi, Wang, Huazheng
Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes. Recent studies followed a non-adaptive setting, where the seed nodes are selected before th
Externí odkaz:
http://arxiv.org/abs/2206.14846
Bilevel optimization have gained growing interests, with numerous applications found in meta learning, minimax games, reinforcement learning, and nested composition optimization. This paper studies the problem of distributed bilevel optimization over
Externí odkaz:
http://arxiv.org/abs/2206.10870