Yi Zhao

I am a postdoctoral researcher in the Robot Learning Lab at Imperial College London, working with Prof. Edward Johns. Before joining Imperial, I was a doctoral researcher in the Robot Learning Group at Aalto University, advised by Prof. Joni Pajarinen and Juho Kannala. I hold an MSc in Robotics from Aalto University and a BEng from Huazhong University of Science and Technology. In 2024, I was a visiting researcher at the Max Planck Institute for Intelligent Systems, where I worked with Prof. Dieter Büchler and Bernhard Schölkopf.

My research focuses on reinforcement learning, imitation learning, and planning, with an emphasis on learning versatile robot skills in a sample-efficient manner. I have developed algorithms that have been applied to various domains, including locomotion, robotic manipulation, and dexterous robotic hands.

Google Scholar
Experience
  • Imperial College London, UK
    Imperial College London, UK
    Postdoctoral Researcher
    Nov. 2025 - now
  • Aalto University, Finland
    Aalto University, Finland
    Doctoral Researcher
    Feb. 2021 - Oct. 2025
  • Max Planck Institute for Intelligent Systems, Germany
    Max Planck Institute for Intelligent Systems, Germany
    Research Visit
    Feb. 2024 - Dec. 2024
  • Aalto University, Finland
    Aalto University, Finland
    Master of Science
    Oct. 2020
  • Huazhong University of Science and Technology, China
    Huazhong University of Science and Technology, China
    Bachelor of Engineering
    June 2017
Publications (view all )
Dexterous Robotic Piano Playing at Scale
Dexterous Robotic Piano Playing at Scale

Le Chen*, Yi Zhao*, Jan Schneider, Quankai Gao, Simon Guist, Cheng Qian, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler (* equal contribution)

Transactions on Pattern Analysis and Machine Intelligence (TPAMI). In Submission 2025

[Paper]

Dexterous Robotic Piano Playing at Scale
Dexterous Robotic Piano Playing at Scale

Le Chen*, Yi Zhao*, Jan Schneider, Quankai Gao, Simon Guist, Cheng Qian, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler (* equal contribution)

Transactions on Pattern Analysis and Machine Intelligence (TPAMI). In Submission 2025

[Paper]

Generative World Modelling for Humanoids Robots
Generative World Modelling for Humanoids Robots

Riccardo Mereu*, Aidan Scannell*, Yuxin Hou, Yi Zhao, Aditya Jitta, Antonio Dominguez, Luigi Acerbi, Amos Storkey, Paul Chang (* equal contribution)

1X World Model Challenge @ ICCV, 1st Place 2025

[Paper] [Website]

Generative World Modelling for Humanoids Robots
Generative World Modelling for Humanoids Robots

Riccardo Mereu*, Aidan Scannell*, Yuxin Hou, Yi Zhao, Aditya Jitta, Antonio Dominguez, Luigi Acerbi, Amos Storkey, Paul Chang (* equal contribution)

1X World Model Challenge @ ICCV, 1st Place 2025

[Paper] [Website]

Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data
Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter Büchler, Arno Solin, Juho Kannala, Joni Pajarinen

Preprint 2025

[Paper]

Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data
Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter Büchler, Arno Solin, Juho Kannala, Joni Pajarinen

Preprint 2025

[Paper]

Symbolically-Guided Visual Plan Inference from Uncurated Video Data
Symbolically-Guided Visual Plan Inference from Uncurated Video Data

Wenyan Yang, Ahmet Tikna, Yi Zhao, Yuying Zhang, Luigi Palopoli, Marco Roveri, Joni Pajarinen

Preprint 2025

[Paper]

Symbolically-Guided Visual Plan Inference from Uncurated Video Data
Symbolically-Guided Visual Plan Inference from Uncurated Video Data

Wenyan Yang, Ahmet Tikna, Yi Zhao, Yuying Zhang, Luigi Palopoli, Marco Roveri, Joni Pajarinen

Preprint 2025

[Paper]

Discrete Codebook World Models for Continuous Control
Discrete Codebook World Models for Continuous Control

Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Sebastian Luck, Arno Solin, Joni Pajarinen

International Conference on Learning Representations (ICLR) 2025

[Paper] [Code] [Website]

Discrete Codebook World Models for Continuous Control
Discrete Codebook World Models for Continuous Control

Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Sebastian Luck, Arno Solin, Joni Pajarinen

International Conference on Learning Representations (ICLR) 2025

[Paper] [Code] [Website]

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands
RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

Yi Zhao*, Le Chen*, Jan Schneider, Quankai Gao, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler (* equal contribution)

Conference on Robot Learning (CoRL) 2024

[Paper] [Website]

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands
RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

Yi Zhao*, Le Chen*, Jan Schneider, Quankai Gao, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler (* equal contribution)

Conference on Robot Learning (CoRL) 2024

[Paper] [Website]

Bi-Level Motion Imitation for Humanoid Robots
Bi-Level Motion Imitation for Humanoid Robots

Wenshuai Zhao, Yi Zhao, Joni Pajarinen, Michael Muehlebach

Conference on Robot Learning (CoRL) 2024

[Paper] [Code]

Bi-Level Motion Imitation for Humanoid Robots
Bi-Level Motion Imitation for Humanoid Robots

Wenshuai Zhao, Yi Zhao, Joni Pajarinen, Michael Muehlebach

Conference on Robot Learning (CoRL) 2024

[Paper] [Code]

iQRL--Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
iQRL--Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen

International Conference on Machine Learning, Workshop (ICML Workshop) 2024

[Paper]

iQRL--Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
iQRL--Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen

International Conference on Machine Learning, Workshop (ICML Workshop) 2024

[Paper]

Optimistic Multi-Agent Policy Gradient
Optimistic Multi-Agent Policy Gradient

Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen

International Conference on Machine Learning (ICML) 2024

[Paper] [Code] [Website]

Optimistic Multi-Agent Policy Gradient
Optimistic Multi-Agent Policy Gradient

Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen

International Conference on Machine Learning (ICML) 2024

[Paper] [Code] [Website]

Hscnet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer
Hscnet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala

International Journal of Computer Vision (IJCV) 2024

[Paper]

Hscnet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer
Hscnet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala

International Journal of Computer Vision (IJCV) 2024

[Paper]

Continuous Monte Carlo Graph Search
Continuous Monte Carlo Graph Search

Kalle Kujanpää*, Amin Babadi*, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen (* equal contribution)

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023

[Paper]

Continuous Monte Carlo Graph Search
Continuous Monte Carlo Graph Search

Kalle Kujanpää*, Amin Babadi*, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen (* equal contribution)

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023

[Paper]

Simplified Temporal Consistency Reinforcement Learning
Simplified Temporal Consistency Reinforcement Learning

Yi Zhao, Wenshuai Zhao, Rinu Boney, Juho Kannala, Joni Pajarinen

International Conference on Machine Learning (ICML) 2023

[Paper] [Code]

Simplified Temporal Consistency Reinforcement Learning
Simplified Temporal Consistency Reinforcement Learning

Yi Zhao, Wenshuai Zhao, Rinu Boney, Juho Kannala, Joni Pajarinen

International Conference on Machine Learning (ICML) 2023

[Paper] [Code]

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Yi Zhao*, Rinu Boney*, Alexander Ilin, Juho Kannala, Joni Pajarinen (* equal contribution)

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2022

[Paper] [Code]

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Yi Zhao*, Rinu Boney*, Alexander Ilin, Juho Kannala, Joni Pajarinen (* equal contribution)

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2022

[Paper] [Code]

Learning to drive (l2d) as a low-cost benchmark for real-world reinforcement learning
Learning to drive (l2d) as a low-cost benchmark for real-world reinforcement learning

Ari Viitala*, Rinu Boney*, Yi Zhao, Alexander Ilin, Juho Kannala (* equal contribution)

International Conference on Advanced Robotics 2021

[Paper] [Website]

Learning to drive (l2d) as a low-cost benchmark for real-world reinforcement learning
Learning to drive (l2d) as a low-cost benchmark for real-world reinforcement learning

Ari Viitala*, Rinu Boney*, Yi Zhao, Alexander Ilin, Juho Kannala (* equal contribution)

International Conference on Advanced Robotics 2021

[Paper] [Website]

Hierarchical scene coordinate classification and regression for visual localization
Hierarchical scene coordinate classification and regression for visual localization

Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

Conference on Computer Vision and Pattern Recognition (CVPR) 2020

[Paper] [Code]

Hierarchical scene coordinate classification and regression for visual localization
Hierarchical scene coordinate classification and regression for visual localization

Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

Conference on Computer Vision and Pattern Recognition (CVPR) 2020

[Paper] [Code]

All publications