Daniele Reda
Email: daniele (dot) reda (at) icloud (dot) com

I am a PhD candidate at University of British Columbia working on learning-based methods for decision-making, planning and control for simulated and real humanoids, character animation, autonomous driving with professor Michiel Van de Panne. During my PhD, I've had the opportunity to collaborate with a lot of cool companies and apply reinforcement learning and physics simulation to different problems. I spent time at Sanctuary AI teaching robots how to use their hands to grasp different objects; at Meta Reality Labs I made animated characters move in virtual worlds; and at Inverted AI I worked on realistic driving simulators. Before, I was a reinforcement learning researcher at Wayve, applying machine learning to robotics control to teach cars how to drive themselves. I completed my B.Sc. at Polytechnic University of Turin and my M.Sc jointly between Polytechnic University of Turin and Telecom ParisTech - Eurecom Research Center, in Sophia Antipolis. I was a visiting researcher at Berkeley AI Research at UC Berkeley where I did research for my master thesis related to graphical models and statistical learning with professor Ruzena Bajcsy. When I am not in front of a screen, I am usually outdoors trying to split myself between rock climbing, hiking, mountaineering, trail running, skiing, and cycling. I always tell myself I should document these adventures more over here, but it rarely happens. CV | Google Scholar | Linkedin | Twitter

publications

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
Guy Tevet, Sigal Raab, Setareh Cohan, Daniele Reda, Zhengyi Luo, Xue Bin Peng, Amit H. Bermano, Michiel van de Panne preprint
project page | arXiv | code

Flexible Motion In-betweening with Diffusion Models
Setareh Cohan, Guy Tevet, Daniele Reda, Xue Bin Peng, Michiel van de Panne
SIGGRAPH 2024
project page | arXiv | code

Physical Simulation of Balance Recovery after a Push
Alexis Jensen, Thomas Chatagnon, Niloofar Khoshsiyar, Daniele Reda, Michiel van de Panne, Charles Pontonnier, Julien Pettré
SIGGRAPH Conference on Motion, Interaction and Games (MIG) 2023
BEST PRESENTATION AWARD
project page

Physics-based Motion Retargeting from Sparse Inputs
Daniele Reda, Jungdam Won, Yuting Ye, Michiel van de Panne, Alexander Winkler
SCA 2023
project page | 2 minute papers feature video!

Learning to Brachiate via Simplified Model Imitation
Daniele Reda*, Hung Yu Ling*, Michiel van de Panne
(* indicates equal contribution)
SIGGRAPH 2022
project page (check the demo!) | 2 minute papers feature video!

Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels
Tianxin Tao*, Daniele Reda*, Michiel van de Panne
(* indicates equal contribution)
ICRA Scaling Robot Learning Workshop 2022
arXiv

Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation
Adam Scibior, Vasileios Lioutas, Daniele Reda, Peyman Bateni, Frank Wood
International Conference on Intelligent Transportation (ITSC) 2021
(Also BEST PAPER AWARD at CVPR Workshop on Autonomous Driving 2021)
arXiv | video

Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning
Daniele Reda*, Tianxin Tao*, Michiel van de Panne
(* indicates equal contribution)
SIGGRAPH Conference on Motion, Interaction and Games (MIG) 2020
arXiv | project page | video

Urban Driving with Conditional Imitation Learning
Jeffrey Hawke* Richard Shen*, Corina Gurau*, Siddharth Sharma*, Daniele Reda*, Nikolay Nikolov*, Przemyslaw Mazur*, Sean Micklethwaite*, Nicolas Griffiths*, Amar Shah*, Alex Kendall*
(* indicates equal contribution)
ICRA 2020
(Also at ML for Autonomous Driving Workshop at NeurIPS 2019 as a contributed talk)
arXiv | blog post | video | video presentation

Learning to Drive in a Day
Alex Kendall, Jeffrey Hawke, David Janz, Przemyslaw Mazur, Daniele Reda, John-Mark Allen, Vinh-Dieu Lam, Alex Bewley, Amar Shah
ICRA 2019
(Also at ML for Intelligent Transportation Systems Workshop at NeurIPS 2018)
arXiv | blog post | video

teaching

• 2023/24 Winter Term 2: CPSC 533V Learning to Move - Reinforcement Learning
• 2021/22 Winter Term 1: CPSC 533V Learning to Move - Reinforcement Learning
• 2021 April: 6th IVADO/MILA Deep Learning School
• 2020/21 Winter Term 2: CPSC 340 Machine Learning and Data Mining
• 2019/20 MDS TA AWARD (certificate)
• 2019/20 Winter Term 2: DSCI 575 Advanced Machine Learning
• 2019/20 Winter Term 2: DSCI 563 Unsupervised Learning
• 2019/20 Winter Term 2: DSCI 572 Supervised Learning II
• 2019/20 Winter Term 2: CPSC 533V Learning to Move - Reinforcement Learning
• 2019 December: IVADO/MILA/DSI Deep Learning School 5th edition
• 2019/20 Winter Term 1: CPSC 422 Intelligent Systems

reviewing

I am/have been a reviewer for NeurIPS, ICML, ICLR, SIGGRAPH, RSS, RAL, ICRA, and various workshops in autonomous driving, reinforcement learning and physics-based simulation.

Last update: June, 2024