Risto Vuorio

Email Github Google Scholar

I got my doctorate from Whiteson Research Lab at University of Oxford where I focused on Meta-Reinforcement Learning (Meta-RL) and imitation learning. I'm excited about developing AI into a practical technology and I believe pushing these directions will help us get there.

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. More recently, I interned at Qualcomm Research Amsterdam supervised by Taco Cohen and others last year.

Selected publications and preprints

A Bayesian Solution To The Imitation Gap

Risto Vuorio (equal contribution), Mattie Fellows (equal contribution), Cong Lu (equal contribution), Clémence Grislain, and Shimon Whiteson. arxiv. 2024. paper

Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control

Zheng Xiong, Risto Vuorio, Jacob Beck, Matthieu Zimmer, Kun Shao, and Shimon Whiteson. ICML. 2024. paper

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. Under review. 2023. paper

Deconfounded Imitation Learning

Risto Vuorio (equal contribution), Pim de Haan (equal contribution), Johann Brehmer, Hanno Ackermann, Daniel Dijkman, and Taco Cohen. arxiv. 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

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

Education

Dphil Computer Science

University of Oxford
Oxford

Fully funded via Scatcherd European Scholarship in conjunction with Engineering and Physical Sciences Research Council Studentship.

M.Sc. Computer Science (with distinction)

Aalto University
Helsinki, Finland

Minor: Mathematics

Thesis: Stream Processing on a Multi-core DSP with Open Event Machine

B.Sc. Industrial Engineering and Management

Aalto University
Helsinki, Finland

Minor: Software technology

Research Experience

Member of Technical Staff

Reflection AI, New York

Intern

Waymo Research, Oxford

Advised by Nico Montali

Intern

Qualcomm Research, Amsterdam

Advised by Taco Cohen, Daniel Dijkman

Visiting Scholar

University of Michigan, Ann Arbor

Advised by Satinder Singh

Research Engineer

SK Telecom, T-Brain

Advised by Jiwon Kim, Joseph J. Lim

Research Assistant

Machine Learning for Big Data Group, Aalto University

Advised by Alexander Jung

Research Assistant

Embedded Systems Group, Aalto University

Advised by Vesa Hirvisalo, Heikki Saikkonen

Industry Experience

Data Scientist/Software Engineer

Wolt Enterprises Oy

Software Engineering Intern / Software Engineer

Apportable Inc

Presentations and appearances

Meta-RL Tutorial AAAI 2024

Presenters: Jacob Beck, Risto Vuorio

Authors: Jacob Beck (equal contribution), Risto Vuorio (equal contribution), Evan Zheran Liu, Zheng Xiong, Luisa Zintgraf, Chelsea Finn, and Shimon Whiteson. Tutorial homepage

Meta-RL Tutorial AutoML 2023

Presenters: Jacob Beck, Risto Vuorio

Authors: Jacob Beck (equal contribution), Risto Vuorio (equal contribution), Evan Zheran Liu, Zheng Xiong, Luisa Zintgraf, Chelsea Finn, and Shimon Whiteson. Tutorial homepage

TalkRL Podcast

Featured as a guest with Jake Beck on TalkRL Podcast.

Service and Activities

Junior Organizer:

NeurIPS Deep RL Workshop 2022.

Program Committee / Reviewer:

ICLR 2024 Workshop on Reliable and Responsible Foundation Models.

ICML 2024 AutoRL Workshop.

ICML 2024 FM-Wild Workshop.

ICML 2022, 2024.

NeurIPS 2023, 2024.

ICLR 2023.

AAAI 2021, 2022.

ICML Pre-Training Workshop 2022.

NeurIPS Deep Reinforcement Learning Workshop 2019, 2020, 2021.

Board member:

TK Ventures 2022, 2023, 2024.