Nicklas Hansen

PhD student, UC San Diego

I am a first-year PhD student at UC San Diego, advised by Prof. Xiaolong Wang and Prof. Hao Su. Before that, I was a visiting student at UC Berkeley and a research intern at Berkeley AI Research, where I was fortunate to work with Prof. Lerrel Pinto, Prof. Xiaolong Wang, and Prof. Alexei Efros.

I received my Bachelor's and Master's degrees from the Technical University of Denmark (DTU), where I worked with Prof. Ole Winther and Prof. Morten Mørup. I have also spent time at Nanyang Technological University (NTUsg) in lovely Singapore, as well as Retune-DSP, and raffle.ai.

Research interest

I am broadly interested in research on the generalization and adaptation of intelligent systems. I believe AI in the future should be flexible, learn with little supervision, and learn continuously over their lifetime. I work with machine learning, robotics, and computer vision.

Publications and preprints

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
Nicklas Hansen, Hao Su, Xiaolong Wang
Conference on Neural Information Processing Systems (NeurIPS), 2021
project page / arXiv / code / bibtex
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Ruihan Yang*, Minghao Zhang*, Nicklas Hansen, Huazhe Xu, Xiaolong Wang
Robotics: Science and Systems (RSS), VLRR Workshop, 2021
project page / arXiv / bibtex
Generalization in Reinforcement Learning by Soft Data Augmentation
Nicklas Hansen, Xiaolong Wang
International Conference on Robotics and Automation (ICRA), 2021
project page / arXiv / code / bibtex
Self-Supervised Policy Adaptation during Deployment
Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang
International Conference on Learning Representations (ICLR), 2021 (Spotlight)
project page / arXiv / blog / code / bibtex
Generalization in Visual Reinforcement Learning
Nicklas Hansen
Master Thesis, 2021
pdf / bibtex
Short Term Blood Glucose Prediction based on Continuous Glucose Monitoring Data
Ali Mohebbi, Alexander R. Johansen, Nicklas Hansen, Peter E. Christensen, Jens M. Tarp, Morten L. Jensen, Henrik Bengtsson, Morten Mørup
Engineering in Medicine and Biology Conference (EMBC), 2020
arXiv / bibtex

Teaching

Reinforcement Learning (Jan 2021)
Technical University of Denmark
Co-organizer
Special course that I co-organized w/ Prof. Ole Winther for a group of students.
Three weeks of full-time study on classical and deep RL.
02456 Deep Learning (Fall 2019, Fall 2020)
Technical University of Denmark
Teaching Assistant
Significant course material contributions, supervised 100+ students’ projects on RL.
website / code
02454 Introduction to Cognitive Science (Fall 2019)
Technical University of Denmark
Teaching Assistant
Assisted tutorial sessions and corrected assignments.
website

Selected open-source projects

DMControl Generalization Benchmark
Nicklas Hansen, Xiaolong Wang
November 2020
project page / arXiv / code / bibtex
Recent Optimization Algorithms for Deep Learning
Nicklas Hansen*, Christoffer Riis*
December 2019
code
How to build RNNs and LSTMs from scratch with NumPy
Nicklas Hansen, Peter E. Christensen, Alexander R. Johansen
October 2019
colab / code
Voice Activity Detection in Noisy Environments
Nicklas Hansen*, Simon H. Albrechtsen*
December 2018
tech report / code / bibtex

Talks

Press coverage

I have been mentioned in various media in connection with my research and my stay at UC Berkeley. Here's a few selected articles:

Mentoring for underrepresented groups

I offer virtual mentoring for high school, undergraduate, and graduate students from underrepresented groups at Danish institutions, preferably with an interest in computer science, research and/or studying abroad. It is free of charge and overseen by a local organization whenever possible. If interested, please reach out to me on the email address below.

Contact

You are very welcome to contact me regarding my research. I typically respond within a few days.
I can be contacted directly at hello [at] nicklashansen .com