Glen Berseth

I am an assistant professor at the University de Montreal and Mila. My research explores how to use deep learning and reinforcement learning to develop generalist robots.

I am an assistant professor at the Université de Montréal, a core academic member of the Mila - Quebec AI Institute, CIFAR AI chair, and co-director of the Robotics and Embodied AI Lab (REAL). I was a Postdoctoral Researcher with Berkeley Artificial Intelligence Research (BAIR), working with Sergey Levine. His previous and current research has focused on solving sequential decision-making problems for real-world autonomous learning systems (robots). The specific of his research has covered the areas of reinforcement-, continual-, meta-, hierarchical learning, and human-robot collaboration. In his work, Dr. Berseth has published at top venues across the disciplines of robotics, machine learning, and computer animation. Currently, he is teaching a course on robot learning at Université de Montréal and Mila that covers the most recent research on machine learning techniques for creating generalist robots.

To see a more formal biography, click here.

Interested in joining the lab?

Are you interested in the practical and theoretical challenges of creating generalist problem-solving robots? Please see this page to apply. I may not respond to emails.

News

Jan 2022: New paper accepted to ICLR on Continual Meta-Reinforcement Learning.
Sep 2021: New paper accepted to CoRL on autonomous robot learning!
Sep 2021: New paper accepted to NeurIPS on surprise minimization in partially observed environments!
Sep 2021: I will be teaching a course on deep reinforcement learning for robotics in January 2022!
May 2021: I will be joining Mila and starting as an assistant professor at the University of Montreal in August 2021!
Apr 2021: Our research paper that will be presented at ICRA2021 on RL for bipedal robots was featured in MIT Technology Review
Mar 2021: Associate Editor for IROS 2021
Feb 2021: Two papers accepted to ICRA2021!
Jan 2021: SMiRL: Surprise Minimizing RL in Unstable Environments receives oral presentation at ICLR 2021 (top 1.8% of submitted papers)
Jan 2021: Two papers accepted to ICLR 2021
Jan 2021: Invited talk at IJCAI workshop Neuro-Cognitive Modeling of Humans and Environments
Aug 2020: Deep Integration of Physical Humanoid Control and Crowd Navigation receives best paper runner up at MIG2020
Sep 2019: Visual Imitation work featured in MIT CSAIL podcast
Apr 2019: Started PostDoc at Berkeley Artificial Intelligence Research (BAIR) group working in the Robotic AI & Learning Lab (RAIL) lab with Sergey Levine
Feb 2019: Defended Ph.D. Thesis at the University of British Columbia under the supervision of Michiel van de Panne
Aug 2017: SIGGRAPH paper DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning covered in the Popular Mechanics.
Mar 2017: Awarded NSERC PhD scholarship
May 2016: Modelling Dynamic Brachiation receives best poster award at Graphics Interfaces 2016
Mar 2016: Robust Space-Time Footsteps for Agent-Based Steering receives best short paper award at CASA 2016

Archives

Tue 08 March 2022: Biography
Sat 12 February 2022: ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning Manipulation
Sat 27 November 2021: Teaching: Robot learning course Schedule
Sun 03 October 2021: Contact
Thu 09 September 2021: Teaching: New course in Robot learning
Wed 08 September 2021: CoMPS: Continual Meta Policy SearchManipulation
Wed 08 September 2021: Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
Tue 10 November 2020: XT2: Training an X-to-Text Typing Interface with Online Learning from Implicit Feedback
Mon 09 November 2020: Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
Sun 08 November 2020: DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies
Sat 10 October 2020: Deep Integration of Physical Humanoid Control and Crowd Navigation
Thu 13 August 2020: Ecological Reinforcement Learning
Thu 13 August 2020: Inter-Level Cooperation in Hierarchical Reinforcement Learning
Thu 12 March 2020: Morphology-Agnostic Visual Robotic Control
Tue 10 December 2019: SMiRL: Surprise Minimizing RL in Unstable Environments
Sat 12 October 2019: Contextual Imagined Goals for Self-Supervised Robotic Learning
Wed 02 October 2019: Interactive Architectural Design with Diverse Solution Exploration
Thu 20 June 2019: Gamification of Crowd-Driven Environment Design
Sat 25 May 2019: Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks
Tue 25 September 2018: Feedback Control for Cassie with Deep Reinforcement Learning
Tue 25 September 2018: Model-Based Action Exploration for Learning Dynamic Motion Skills
Thu 05 April 2018: TerrainRL Sim
Tue 06 February 2018: Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
Wed 10 January 2018: Demystifying the Many Deep Reinforcement Learning Algorithms
Tue 14 November 2017: Evaluating and Optimizing Evacuation Plans for Crowd Egress
Sun 14 May 2017: DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning
Sun 14 May 2017: Interfacing with Simulators for RL
Mon 14 November 2016: Towards Computer Assisted Crowd Aware Architectural Design
Sat 14 May 2016: Using synthetic crowds to inform building pillar placements
Sat 14 May 2016: Dynamic terrain traversal skills using reinforcement learning
Sat 14 May 2016: Modelling Dynamic Brachiation
Sat 14 May 2016: Terrain Adaptive Locomotion Skills using Deep Reinforcement Learning
Thu 14 April 2016: ACCLMesh: Curvature-Based Navigation Mesh Generation
Sat 21 November 2015: Basic Reinforcement Learning Example using Logistic Regression
Sun 25 October 2015: Using SWIG to wrap C++ for Python
Wed 21 October 2015: Animation/Simulation System flow of control
Wed 20 May 2015: Evaluating and Optimizing Level of Service for Crowd Evacuations
Mon 04 May 2015: Handling Segfaults in Python that occur in custom C++ libraries
Fri 01 May 2015: Knowledge vs Information
Tue 14 April 2015: Asynchronous Real-time Multiplayer Game (ARM Game)
Wed 18 March 2015: Install eclipse plugins via the command line
Mon 09 March 2015: Crowd Simulation Lecture
Sun 21 December 2014: High Resolution performance timer
Sun 12 October 2014: Mesh Subdivision with the Loop Algorithm
Sat 06 September 2014: Install SciPy on Mac OS
Thu 14 August 2014: Spelling and Grammar Checking for Latex
Fri 20 June 2014: Characterizing and Optimizing Game Level Difficulty
Tue 20 May 2014: Environment Optimization for Crowd Evacuation
Tue 20 May 2014: Optimizing Simulated Crowd Behaviour
Tue 20 May 2014: Robust Space-time Footsteps for Agent-based Steering
Tue 20 May 2014: SteerFit
Tue 20 May 2014: SteerPlex
Tue 20 May 2014: Unreal IndiGolog Bot Project
Thu 14 November 2013: Digit Reconition using a Multi-Layer Perceptron
Tue 03 September 2013: Generating Latex table of Matlab/Octave Matrix
Mon 20 May 2013: Research in Unique Satisfiability
Sun 19 May 2013: psycopg2 instering an array of polygons
Sun 19 May 2013: 'Postgresql: Calculate the number of polygon islands or overlapping groups'
Sun 21 April 2013: Install Twiki on Ubuntu 12.04
Wed 17 April 2013: Putting a steering algorithm into SteerSuite
Tue 19 March 2013: Postgresql Transfer Database to New Tablespace with Python
Sat 09 March 2013: Rare but powerful Unix/Linux commands
Fri 08 March 2013: SmartBody, first steps
Fri 08 March 2013: Eclipse Find/Replace
Wed 06 March 2013: 'SmartBody Example:'
Sun 03 March 2013: 'plpgsql: Creating Functions and saving intermetiate query results'
Fri 22 February 2013: IndiGolog Basics
Thu 21 February 2013: Install/setup Postgres 9.1 on Ubuntu 12.04
Wed 20 February 2013: Python and TCP/IP
Wed 20 February 2013: Get and Compile Smart Body
Thu 07 February 2013: Ubuntu 12.04 on ASUS n56v
Sun 20 May 2012: GpsdInspector
Sun 20 May 2012: Unreal Environment Interface
Fri 10 December 2010: Info
Fri 10 December 2010: Links