Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Jia Zeyu"'
Autor:
Zhong Hao, Xing Cong, Zhou Mi, Jia Zeyu, Liu Song, Zhu Shibo, Li Bo, Yang Hongjiang, Ma Hongpeng, Wang Liyue, Zhu Rusen, Qu Zhigang, Ning Guangzhi
Publikováno v:
Acta Biochimica et Biophysica Sinica, Vol 55, Pp 1718-1729 (2023)
As a commonly used physical intervention, electrical stimulation (ES) has been demonstrated to be effective in the treatment of central nervous system disorders. Currently, researchers are studying the effects of electrical stimulation on individual
Externí odkaz:
https://doaj.org/article/adb1c027965e44c08aa42419331a9e54
We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax bounds, we show that the eluder dimension $d_\text{elu}$$-$a compl
Externí odkaz:
http://arxiv.org/abs/2410.12713
We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al. (2022) left open the question whether a bounded concentrability coeff
Externí odkaz:
http://arxiv.org/abs/2403.17091
We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an $\epsilon$-suboptimal policy w
Externí odkaz:
http://arxiv.org/abs/2310.06113
We consider the question of estimating multi-dimensional Gaussian mixtures (GM) with compactly supported or subgaussian mixing distributions. Minimax estimation rate for this class (under Hellinger, TV and KL divergences) is a long-standing open ques
Externí odkaz:
http://arxiv.org/abs/2306.12308
We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping. Unfortunately, however, based on only this assumption, the w
Externí odkaz:
http://arxiv.org/abs/2211.07419
Consider an empirical measure $\mathbb{P}_n$ induced by $n$ iid samples from a $d$-dimensional $K$-subgaussian distribution $\mathbb{P}$ and let $\gamma = N(0,\sigma^2 I_d)$ be the isotropic Gaussian measure. We study the speed of convergence of the
Externí odkaz:
http://arxiv.org/abs/2205.02128
It has long been thought that high-dimensional data encountered in many practical machine learning tasks have low-dimensional structure, i.e., the manifold hypothesis holds. A natural question, thus, is to estimate the intrinsic dimension of a given
Externí odkaz:
http://arxiv.org/abs/2106.04018
Autor:
Zhang, Dongwei, Yang, Xinyu, Li, Hang, Jia, Zeyu, Zhang, Shoubing, Tang, Songzhen, Liu, Deping, Wu, Xuehong
Publikováno v:
In Energy Conversion and Management 1 February 2024 301
This paper studies model-based reinforcement learning (RL) for regret minimization. We focus on finite-horizon episodic RL where the transition model $P$ belongs to a known family of models $\mathcal{P}$, a special case of which is when models in $\m
Externí odkaz:
http://arxiv.org/abs/2006.01107