I am a Ph.D. student at Whiteson Research Lab at University of Oxford. My research is focused on Meta-Reinforcement Learning (Meta-RL). I'm excited about developing Deep RL into a practical technology and I believe Meta-RL is a good framework for making progress on that.
Risto Vuorio
Before joining WhiRL, I worked with Satinder Singh at the University of Michigan on meta-gradient reinforcement learning. And before that, I worked at SK-Telecom AI Research Lab in Seoul. I got my Master's in Computer Science at Aalto University, Finland.
Publications
A Survey of Meta-Reinforcement Learning
Jacob Beck (equal contribution), Risto Vuorio (equal contribution), Evan Zheran Liu, Zheng Xiong, Luisa Zintgraf, Chelsea Finn, and Shimon Whiteson. arxiv. 2023. paper
Deconfounded Imitation Learning
Risto Vuorio, Johann Brehmer, Hanno Ackermann, Daniel Dijkman, Taco Cohen, and Pim de Haan. NeurIPS Deep RL Workshop. 2022. paper
Hypernetworks in Meta-Reinforcement Learning
Jacob Beck, Matthew Thomas Jackson, Risto Vuorio, and Shimon Whiteson. Conference on Robot Learning (CoRL). 2022. paper
Pairwise Weights for Temporal Credit Assignment
Zeyu Zheng (equal contribution), Risto Vuorio (equal contribution), Richard Lewis, and Satinder Singh. AAAI. 2022. paper
An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
Risto Vuorio, Jacob Beck, Gregory Farquhar, Jakob Foerster, Shimon Whiteson. NeurIPS Deep RL Workshop. 2021. paper
Learning State Representations from Random Deep Action-conditional Predictions
Zeyu Zheng, Vivek Veeriah, Risto Vuorio, Richard Lewis, Satinder Singh. NeurIPS. 2021. paper
On the Practical Consistency of Meta-Reinforcement Learning Algorithms
Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio, Shimon Whiteson. NeurIPS Meta-Learning Workshop. 2021.
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Risto Vuorio (equal contribution), Shao-Hua Sun (equal contribution), Hexiang Hu, and Joseph J. Lim. NeurIPS (Spotlight). 2019. paper
Deep Reinforcement Learning for Dynamic Multi-Driver Dispatching and Repositioning Problem
John Holler (equal contribution), Risto Vuorio (equal contribution), Tiancheng Jin, Satinder Singh, Zhiwei Qin, Jieping Ye, Xiaocheng Tang, Yan Jiao, and Chenxi Wang. ICDM Short Paper. 2019. paper
Toward Multimodal Model-Agnostic Meta-Learning
Risto Vuorio, Shao-Hua Sun, Hexiang Hu and Joseph J. Lim. NeurIPS Meta-Learning Workshop. 2018. paper
Meta Continual Learning
Risto Vuorio, Subin Yi, Dong-Yeon Cho, Daejoong Kim and Jiwon Kim. NeurIPS Continual Learning Workshop. 2018. paper
Education
Ph.D. Computer Science
University of Oxford OxfordM.Sc. Computer Science (with distinction)
Aalto University Helsinki, FinlandMinor: Mathematics
Thesis: Stream Processing on a Multi-core DSP with Open Event Machine
B.Sc. Industrial Management
Aalto University Helsinki, FinlandMinor: Software Technology
Research Experience
Research Intern
Qualcomm Research, AmsterdamAdvised by Taco Cohen, Daniel Dijkman
Visiting Scholar
University of Michigan, Ann ArborAdvised by Satinder Singh
Research Engineer
SK Telecom, T-BrainAdvised by Jiwon Kim, Joseph J. Lim
Research Assistant
Machine Learning for Big Data Group, Aalto UniversityAdvised by Alexander Jung
Research Assistant
Embedded Systems Group, Aalto UniversityAdvised by Vesa Hirvisalo, Heikki Saikkonen
Industry Experience
Data Scientist/Software Engineer
Wolt Enterprises OySoftware Engineer
Apportable IncService and Activities
Junior Organizer:
NeurIPS Deep RL Workshop 2022.
Program Committee:
ICML 2022.
AAAI 2021, 2022.
NeurIPS Deep Reinforcement Learning Workshop 2019, 2020, 2021.
ICML Pre-Training Workshop 2022.