Preprint
  1. Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
    Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, and Koushil Sreenath

    Under submission
    arXiv Video
  2. Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
    Adriana Knatchbull-Hugessen, Roger Creus-Castanyer, and Glen Berseth

    Intrinsically-Motivated and Open-Ended Learning Workshop at NeurIPS2023
    [Link]
  3. Inter-Level Cooperation in Hierarchical Reinforcement Learning
    Abdul Rahman Kreidieh, Glen Berseth, Brandon Traboco Samyak Parajuli, Sergey Levine, and Alexandre M. Bayen

    Under submission to Journal of Machine Learning Research
    arXiv
2024
  1. Improving Intrinsic Exploration by Creating Stationary Objectives
    Roger Creus Castanyer, Joshua Romoff, and Glen Berseth

    In The Twelfth International Conference on Learning Representations
    arXiv [Link]
  2. Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View
    Raj Ghugare, Matthieu Geist, Benjamin Eysenbach, and Glen Berseth

    In The Twelfth International Conference on Learning Representations
    arXiv [Link]
  3. Intelligent Switching for Reset-Free RL
    Darshan Patil, Janarthanan Rajendran, Glen Berseth, and Sarath Chandar

    In The Twelfth International Conference on Learning Representations
    [Link]
  4. Searching the space of high-value molecules using reinforcement learning and language models
    Raj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, and Glen Berseth

    In The Twelfth International Conference on Learning Representations
    arXiv [Link]
  5. Reasoning with Latent Diffusion in Offline Reinforcement Learning
    Siddarth Venkatraman, Shivesh Khaitan, Ravi Tej Akella, John Dolan, Jeff Schneider, and Glen Berseth

    In The Twelfth International Conference on Learning Representations
    arXiv [Link]
2023
  1. Maximum State Entropy Exploration using Predecessor and Successor Representations
    Arnav Kumar Jain, Lucas Lehnert, Irina Rish, and Glen Berseth

    In Thirty-seventh Conference on Neural Information Processing Systems
    arXiv [Link]
  2. Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
    Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, and Sergey Levine

    In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2023)
    arXiv Project Page
  3. Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer
    Donghyeon Kim, Glen Berseth, Mathew Schwartz, and Jaeheung Park

    IEEE Robotics and Automation Letters
    arXiv Video
  4. Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
    Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, and Koushil Sreenath

    In Robotics: Science and Systems XIX, Daegu, Republic of Korea, July 10-14, 2023
    arXiv [Link] Video
  5. Towards Learning to Imitate from a Single Video Demonstration
    Glen Berseth, Florian Golemo, and Christopher Pal

    J. Mach. Learn. Res.
    [HTML] [Link] Project Page Video
2022
  1. Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot
    Yandong Ji, Zhongyu Li*, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, and Koushil Sreenath

    In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2022)
    arXiv Video
  2. AnyMorph: Learning Transferable Policies By Inferring Agent Morphology
    Brandon Trabucco, Phielipp Mariano, and Glen Berseth

    Internation Conference on Machine Learning
    arXiv Project Page
  3. ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
    Sean Chen*, Jensen Gao*, Siddharth Reddy, Glen Berseth, Anca D. Dragan, and Sergey Levine

    IEEE International Conference on Robotics and Automation (ICRA)
    arXiv [Link] Project Page Code Video
  4. CoMPS: Continual Meta Policy Search
    Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, and Sergey Levine

    In International Conference on Learning Representations
    arXiv [Link] Project Page Video
2021
  1. Explore and Control with Adversarial Surprise
    Arnaud Fickinger, Natasha Jaques, Samyak Parajuli, Michael Chang, Nicholas Rhinehart, Glen Berseth, Stuart Russell, and Sergey Levine

    CoRR
    arXiv [Link] Project Page Video
  2. Intrinsic Control of Variational Beliefs in Dynamic Partially-Observed Visual Environments
    Nicholas Rhinehart, Jenny Wang, Glen Berseth, John D Co-Reyes, Danijar Hafner, Chelsea Finn, and Sergey Levine

    In Advances in Neural Information Processing Systems
  3. Accelerating Online Reinforcement Learning via Model-Based Meta-Learning
    John D Co-Reyes, Sarah Feng, Glen Berseth, Jie Qui, and Sergey Levine

    In Learning to Learn - Workshop at ICLR 2021
    [Link]
  4. DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies
    Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair, Alexander Khazatsky, Glen Berseth, and Sergey Levine

    International Conference on Robotics and Automation (ICRA 2021)
    arXiv [Link] Project Page
  5. Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
    Charles Sun, Coline Devin, Brian Yang, Jędrzej Orbik, Abhishek Gupta, Glen Berseth, and Sergey Levine

    In Conference on Robot Learning (CoRL)
    Video
  6. SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
    Glen Berseth, Daniel Geng, Coline Manon Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, and Sergey Levine


    arXiv [Link] Project Page Video
2020
  1. X2T: Training an X-to-Text Typing Interface with Online Learning from Implicit Feedback
    Jensen Gao, Sid Reddy, Glen Berseth, Anca Dragon, and Sergey Levine

    International Conference on Learning Representations (ICLR) 2021
  2. Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
    Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, and Koushil Sreenath

    International Conference on Robotics and Automation (ICRA 2021)
  3. Ecological Reinforcement Learning
    John D. Co-Reyes, Suvansh Sanjeev, Glen Berseth, Abhishek Gupta, and Sergey Levine

    CoRR
    [Link]
  4. Gamification of Crowd-Driven Environment Design
    Michael Brandon Haworth, Muhammad Usman, Davide Schaumann, Nilay Chakraborty, Berseth Glen, Petros Faloutsos, and Mubbasir Kapadia

    IEEE Computer Graphics and Applications
  5. Morphology-Agnostic Visual Robotic Control
    Brian Yang, Dinesh Jayaraman, Berseth Glen, Alexei Efros, and Sergey Levine

    IEEE Robotics and Automation Letters
  6. Deep Integration of Physical Humanoid Control and Crowd Navigation (\textbfbest paper runner up)
    Berseth Glen *, Brandon Haworth*, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the 13th International Conference on Motion in Games
2019
  1. Contextual Imagined Goals for Self-Supervised Robotic Learning
    Ashvin Nair^*, Shikhar Bahl^*, Alexander Khazatsky^*, Vitchyr Pong, Glen Berseth, and Sergey Levine

    In Conference on Robot Learning (CoRL)
    arXiv Project Page Video
  2. Interactive Architectural Design with Diverse Solution Exploration
    Glen Berseth, Brandon Haworth, Muhammad Usman, Davide Schaumann, Mahyar Khayatkhoei, Mubbasir Kapadia, and Petros Faloutsos

    IEEE Transactions on Visualization and Computer Graphics
    Video
2018
  1. Terrain RL Simulator
    Glen Berseth, Xue Bin Peng, and Michiel Panne

    CoRR
    [Link]
  2. Feedback Control For Cassie With Deep Reinforcement Learning
    Zhaoming Xie, Glen Berseth, Patrick Clary, Jonathan W. Hurst, and Michiel Panne

    In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2018)
  3. Model-Based Action Exploration for Learning Dynamic Motion Skills
    Glen Berseth, Alex Kyriazis, Ivan Zinin, William Choi, and Michiel Panne

    In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2018)
    Video
  4. Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
    Glen Berseth, Cheng Xie, Paul Cernek, and Michiel Van Panne

    International Conference on Learning Representations (ICLR) 2018
    Video
2017
  1. Evaluating and optimizing evacuation plans for crowd egress
    Vincius J Cassol, Estêvão Smania Testa, Cláudio Rosito Jung, Muhammad Usman, Petros Faloutsos, Berseth Glen, Mubbasir Kapadia, Norman I Badler, and Soraia Raupp Musse

    IEEE computer graphics and applications
  2. Perceptual Evaluation of Space in Virtual Environments
    Muhammad Usman, Brandon Haworth, Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the Tenth International Conference on Motion in Games
  3. Crowd Sourced Co-design of Floor Plans Using Simulation Guided Games
    Nilay Chakraborty, Brandon Haworth, Muhammad Usman, Berseth Glen, Petros Faloutsos, and Mubbasir Kapadia

    In Proceedings of the Tenth International Conference on Motion in Games
  4. On density flow relationships during crowd evacuation
    Brandon Haworth, Muhammad Usman, Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    Computer Animation and Virtual Worlds 28 (3-4)
  5. DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning
    Xue Bin Peng, Berseth Glen, KangKang Yin, and Michiel Panne

    SIGGRAPH 2017
  6. Understanding spatial perception and visual modes in the review of architectural designs
    Muhammad Usman, Brandon Haworth, Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 31
  7. CODE: Crowd Optimized Design of Environments
    Brandon Haworth, Muhammad Usman, Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    Computer Animation and Virtual Worlds
2016
  1. ACCLMesh: curvature-based navigation mesh generation
    Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    Computer Animation and Virtual Worlds
  2. Terrain-adaptive locomotion skills using deep reinforcement learning
    Xue Bin Peng, Berseth Glen, and Michiel Panne

    ACM Transactions on Graphics (TOG)
  3. Using synthetic crowds to inform building pillar placements
    Brandon Haworth, Muhammad Usman, Berseth Glen, Mahyar Khayatkhoei, Mubbasir Kapadia, and Petros Faloutsos

    In Virtual Humans and Crowds for Immersive Environments (VHCIE), IEEE
  4. Towards Computer Assisted Crowd Aware Architectural Design
    Brandon Haworth, Muhammad Usman, Berseth Glen, Mahyar Khayatkhoei, Mubbasir Kapadia, and Petros Faloutsos

    In CHI ’16 Extended Abstracts
    [Link]
2015
  1. Dynamic Terrain Traversal Skills Using Reinforcement Learning
    Xue Bin Peng, Berseth Glen, and Michiel Panne

    ACM Trans. Graph.
    [Link]
  2. Environment optimization for crowd evacuation
    Berseth Glen, Muhammad Usman, Brandon Haworth, Mubbasir Kapadia, and Petros Faloutsos

    Computer Animation and Virtual Worlds
    [Link] Video
  3. Robust Space-Time Footsteps for Agent-Based Steering (best short paper)
    Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    Computer Animation and Virtual Worlds
    Video
  4. ACCLMesh: Curvature-based Navigation Mesh Generation
    Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games
    [Link]
  5. Evaluating and Optimizing Level of Service for Crowd Evacuations
    Brandon Haworth, Muhammad Usman, Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games
    [Link]
2014
  1. Characterizing and Optimizing Game Level Difficulty
    Berseth Glen, M. Brandon Haworth, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of the Seventh International Conference on Motion in Games
    [Link]
  2. SteerFit: Automated Parameter Fitting for Steering Algorithms
    Glen Berseth, Mubbasir Kapadia, Brandon Haworth, and Petros Faloutsos

    In Eurographics/ ACM SIGGRAPH Symposium on Computer Animation
    [Link]
2013
  1. SteerPlex: Estimating Scenario Complexity for Simulated Crowds
    Berseth Glen, Mubbasir Kapadia, and Petros Faloutsos

    In Proceedings of Motion on Games
    [Link]