Výsledky vyhledávání

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning

Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative offline R

Externí odkaz: http://arxiv.org/abs/2406.07541

Zobrazit plný text záznamu

Report

World Models with Hints of Large Language Models for Goal Achieving

Autor: Liu, Zeyuan, Huan, Ziyu, Wang, Xiyao, Lyu, Jiafei, Tao, Jian, Li, Xiu, Huang, Furong, Xu, Huazhe

Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful guidance in

Externí odkaz: http://arxiv.org/abs/2406.07381

Zobrazit plný text záznamu

Report

Adaptive Boosting with Fairness-aware Reweighting Technique for Fair Classification

Autor: Song, Xiaobin, Liu, Zeyuan, Jiang, Benben

Machine learning methods based on AdaBoost have been widely applied to various classification problems across many mission-critical applications including healthcare, law and finance. However, there is a growing concern about the unfairness and discr

Externí odkaz: http://arxiv.org/abs/2401.03097

Zobrazit plný text záznamu

Report

Multi-Agent Coordination via Multi-Level Communication

Autor: Ding, Ziluo, Liu, Zeyuan, Fang, Zhirui, Su, Kefan, Zhu, Liwen, Lu, Zongqing

The partial observability and stochasticity in multi-agent settings can be mitigated by accessing more information about others via communication. However, the coordination problem still exists since agents cannot communicate actual actions with each

Externí odkaz: http://arxiv.org/abs/2209.12713

Zobrazit plný text záznamu

Analysis of the dynamics and influence of the research work of Prof. Liu Zeyuan in China featuring a new hybrid approach combining community detection with topic tracking

Autor: Yuqi Wang, Jean-Charles Lamirel, Pascal Cuxac, Nicolas Dugué, Anthony Perez, Younes Gueddari

Publikováno v: Scientometrics
Scientometrics, 2021, 126 (7), pp.6273-6300. ⟨10.1007/s11192-021-04010-0⟩
Scientometrics, Springer Verlag, 2021, 126 (7), pp.6273-6300. ⟨10.1007/s11192-021-04010-0⟩

International audience; The influence of authors is mostly based on their capacity to form specific self-contained and/or active research communities or topics while also inspiring fruitful spin-off research derived from those communities or topics.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b14486822d7cb18ab1f39a359104958
https://hal.science/hal-03285158

Zobrazit plný text záznamu