Personal information

Emails & domains

Verified email addresses

Verified email domains

Websites & social links

Personal Website
Github
LinkedIn

Keywords

Reinforcement Learning, Continual Learning

Biography

I am interested in developing simple and efficient algorithms supported by sound theories and verified by rigorous experiments. In particular, my research focuses on designing continual (reinforcement) learning algorithms with higher sample, memory, and computation efficiency. I have also worked on meta-learning, exploration, language modeling, and quantum reinforcement learning.

Activities

Collapse all

Education and qualifications (4)

University of Oxford: Oxford, Oxfordshire, GB

(St Edmund Hall)
Education
Source: check_circle
ORCID Integration at the University of Oxford

University of Alberta: Edmonton, CA

2020-09 to present | PhD (Department of Computing Science)
Education
Source: Self-asserted source
Qingfeng Lan

University of Alberta: Edmonton, CA

2018-09 to 2020-09 | Master (Department of Computing Science)
Education
Source: Self-asserted source
Qingfeng Lan

University of the Chinese Academy of Sciences: Beijing, CN

2014-09 to 2018-07 | Bachelor
Education
Source: Self-asserted source
Qingfeng Lan

Works (1)

Maxmin Q-learning: Controlling the Estimation Bias of Q-learning

International Conference on Learning Representations
2020 | Conference paper
URI:

https://openreview.net/forum?id=Bkg0u3Etwr
Contributors: Qingfeng Lan; Yangchen Pan; Alona Fyshe; Martha White
Source: Self-asserted source
Qingfeng Lan
How many people are using ORCID?