1、個(gè)人基本信息：

姓 名：趙陽洋

性 別：女

出生年月：1995.12

技術(shù)職稱：講師

畢業(yè)院校：華南理工大學(xué)

學(xué)歷（學(xué)位）：博士研究生

所在學(xué)科：軟件工程

研究方向：人工智能、人機(jī)對(duì)話、自然語言處理、機(jī)器學(xué)習(xí)、強(qiáng)化學(xué)習(xí)

2、教育背景：

2021.11-2022.11

烏特勒支大學(xué)

聯(lián)合培養(yǎng)博士

2017.09-2022.12

華南理工大學(xué)

博士

2013.09-2017.06

廣州中醫(yī)藥大學(xué)

學(xué)士

3、目前研究領(lǐng)域：

人工智能、人機(jī)對(duì)話、自然語言處理、機(jī)器學(xué)習(xí)、強(qiáng)化學(xué)習(xí)

4、已完成或已在承擔(dān)的主要課題：

基于端云融合的網(wǎng)聯(lián)協(xié)同控制關(guān)鍵技術(shù)研究及應(yīng)用，廣東省重點(diǎn)領(lǐng)域研發(fā)計(jì)劃項(xiàng)目，新一代人工智能專項(xiàng)，參與，10000萬元

面向在線社會(huì)網(wǎng)絡(luò)的信息傳播結(jié)構(gòu)分析與宏觀預(yù)測(cè)，廣東省基礎(chǔ)與應(yīng)用基礎(chǔ)研究基金，面上項(xiàng)目，參與，10萬元

基于大數(shù)據(jù)分析的移動(dòng)音樂智能搜索與推薦平臺(tái)，廣州市科技計(jì)劃項(xiàng)目，廣州市產(chǎn)業(yè)技術(shù)重大攻關(guān)計(jì)劃-現(xiàn)代產(chǎn)業(yè)技術(shù)專題項(xiàng)目，參與，1400萬元

面向移動(dòng)互聯(lián)網(wǎng)用戶大數(shù)據(jù)分析及推薦平臺(tái)的產(chǎn)業(yè)化應(yīng)用，廣東省應(yīng)用型科技研發(fā)專項(xiàng)資金項(xiàng)目重點(diǎn)項(xiàng)目，參與，400萬元

6、已發(fā)表的學(xué)術(shù)論文：

[1] Yangyang Zhao,   Zhenyu Wang*, Zhenhua Huang. Automatic Curriculum Learning With   Over-repetition Penalty for Dialogue Policy Learning. AAAI 2021. (CCF-A)

[2] Yangyang Zhao,   Zhenyu Wang*, Kai Yin, Rui Zhang, Zhenhua Huang, Pei Wang. Dynamic   Reward-based Dueling Deep Dyna-Q: Robust Policy Learning in Noisy   Environments. AAAI 2020. (CCF-A)

[3] 趙陽洋，王振宇*，王佩，楊添，張睿，尹凱. 任務(wù)型對(duì)話系統(tǒng)研究綜述. 計(jì)算機(jī)學(xué)報(bào), 2020, 43(10): 1862-1896. (CCF-A)

[4] Yangyang Zhao, Zhenyu   Wang *, Changxi Zhu, Shihan Wang. Complementary Policy Learning from Episodic   Memory Policy and DQN Policy. EMNLP 2021. (CCF-B)

[5] Yangyang Zhao, Hua   Qin, Zhenyu Wang*, Changxi Zhu, Shihan Wang*. A Versatile Adaptive Curriculum   Learning Framework for Task-oriented Dialogue Policy Learning. NAACL 2022.   (CCF-B)

[6] Hui Zhu, Yangyang Zhao*, Qin   Hua*. Cold-started Curriculum Learning for Task-oriented Dialogue Policy.   IEEE ICEBE 2021. (EI)

[7] 朱映波，趙陽洋，王佩，尹凱，王振宇. 融合馬爾科夫決策過程與信息熵的對(duì)話策略. 計(jì)算機(jī)工程, 2021, 47(3):284-290. (中文核心)

[8] Zhenhua Huang, Zhenyu Wang*,   Rui Zhang, Yangyang Zhao, Fadong Zheng. Learning Bi-directional Social   Influence in Information Cascades using Graph Sequence Attention Networks.   In: The 2020 Conference of International World Wide Web, student abstract,   2020. (CCF-A)

[9] Zhenhua Huang, Zhenyu Wang*,   Rui Zhang, Yangyang Zhao, Xiaohui Xie, Sharad Mehrotra. Network2Vec:   Learning Node Representation Based on Space Mapping in Networks. In: The 2019   Conference of IEEE International Conference on Data Mining, workshop, 2019. (CCF-B)

[10] Zhenhua Huang, Junxian Wu,   Wentao Zhu, Zhenyu Wang*, Sharad Mehrotra, Yangyang Zhao. Visualizing   Complex Networks by Leveraging Community Structures. Physica A: Statistical   Mechanics and its Applications, 2021, 565: 125506.(SCI 二區(qū))

[11] Rui Zhang, Zhenyu Wang*,   Mengdan Zheng, Yangyang Zhao, Zhenhua Huang. Emotion-Sensitive Deep   Dyna-Q Learning for Task-Completion Dialogue Policy Learning. Neurocomputing,   2021, 459: 122-130. (SCI 二區(qū))

7、 所獲學(xué)術(shù)榮譽(yù)及學(xué)術(shù)影響：

\