白辰甲  (Chenjia Bai)

New HomePage

博士研究生
哈尔滨工业大学模式识别研究中心

教育经历

2011-2015 本科 哈尔滨工业大学  计算机科学与技术学院

2015-2017 硕士 哈尔滨工业大学 计算机科学与技术学院 thesis.zip

2017-2022 博士 哈尔滨工业大学 计算机科学与技术学院

实习经历

2016.6-2016.9 阿里巴巴集团实习 算法工程师

2020.6-2020.9  华为诺亚方舟研究院（Noah's Ark Lab）决策与推理实验室

2020.11-2021.3  腾讯 AI Lab & Robotics X

Project & Talks

三维立体测量仪

智能车避障方法研究

Pixel RNN for Reinforcement Learningprl.pdf

Hinsight & Hierarchical Reinforcement Learning HER-HRL.pdf

Multi-task & Transfer & Lifelong Reinforcement LearningMulti-task.pdf

RL for Localization & Navigation & Building map Papers  RL-navigation.pdf

Exploration & Exploitation for Reinforcement Learning exploration.pdf.zip

Uncertainty in Reinforcement Learning Uncertainty.pdf.zip

Representation for Reinforcement LearningRepresentation-RL.pdf.zip

Summary of Exploration Methods in DRL (2020-7-20)exploration-rl.pptx.zip

Publication

[1] 白辰甲，刘鹏，赵巍，唐降龙. 基于TD-error自适应矫正的深度Q学习主动采样方法[J]. 计算机研究与发展, 2019, 56(2): 262-280. (EI收录) (PDF, 相关文件)

[2]  Chenjia Bai, Peng Liu, Wei Zhao, Xianglong Tang. Guided goal generation for hindsight multi-goal reinforcement learning. Neurocomputing. 2019 (IF=3.2, JCR-1, CCF-C).https://doi.org/10.1016/j.neucom.2019.06.022

[3] Peng Liu, Chenjia Bai, Yingnan Zhao, et al. Generating attentive goals for prioritized hindsight reinforcement learning. Knowledge-Based Systems. 2020. (203):106140 (IF-5.1, JCR-1, CCF-C) https://doi.org/10.1016/j.knosys.2020.106140

[4] Chenjia Bai, Peng Liu, Zhaoran Wang, et al. Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. ( JCR-1, CCF-B, IF=8.8)

[5] Chenjia Bai, Lingxiao Wang, Yixin Wang, et al. Addressing Hindsight Bias in Multi-Goal Reinforcement Learning. IEEE Transactions on Cybernetics, 2021 ( JCR-1, CCF-B, IF=11.1)

[6] Chenjia Bai, Lingxiao Wang, Zhaoran Wang, et al. Principled Exploration via Optimistic Bootstrapping and Backward Induction. International Conference on Machine Learning (ICML), 2021 (已录用, CCF-A)

[7] Chenjia Bai, Lingxiao Wang, Lei Han, et al. Dynamic Bottleneck for Robust Self-Supervised Exploration. Neural Information Processing Systems (NeurIPS), 2021 (已录用，CCF-A)

[8] Chenjia Bai, Lingxiao Wang, Zhuoran Yang, Zhihong Deng, Animesh Garg, Peng Liu, and Zhaoran Wang. Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning. International Conference on Learning Representations (ICLR), 2022

[9] Shuang Qiu, Lingxiao Wang, Chenjia Bai, Zhuoran Yang, and Zhaoran Wang. Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning. International Conference on Machine Learning (ICML), 2022 (CCF-A类会议)

[10] Chenjia Bai, Ting Xiao, Zhoufan Zhu, Lingxiao Wang, Fan Zhou, Peng Liu, and Zhaoran Wang. Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems , 2022 (中科院一区Top期刊，CCF-B类，IF=14.3)

[11]Jianye Hao, Tianpei Yang, Hongyao Tang, Chenjia Bai, Jinyi Liu, Zhaopeng Meng, Peng Liu, and Zhen Wang. Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain. IEEE Transactions on Neural Networks and Learning Systems, 2022 (中科院一区Top期刊，CCF-B类，IF=14.3)

联系方式

bai_chenjia@163.com

Github link

Google Scholar link