Publications
Preprint
Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
Intrinsically-Motivated and Open-Ended Learning Workshop at NeurIPS2023
[Link]Inter-Level Cooperation in Hierarchical Reinforcement Learning
Under submission to Journal of Machine Learning Research
arXiv
2024
Intelligent Switching for Reset-Free RL
In The Twelfth International Conference on Learning Representations
[Link]
2023
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2023)
arXiv Project PageTowards Learning to Imitate from a Single Video Demonstration
J. Mach. Learn. Res.
[HTML] [Link] Project Page Video
2022
AnyMorph: Learning Transferable Policies By Inferring Agent Morphology
Internation Conference on Machine Learning
arXiv Project PageASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
IEEE International Conference on Robotics and Automation (ICRA)
arXiv [Link] Project Page Code VideoCoMPS: Continual Meta Policy Search
In International Conference on Learning Representations
arXiv [Link] Project Page Video
2021
Explore and Control with Adversarial Surprise
CoRR
arXiv [Link] Project Page VideoIntrinsic Control of Variational Beliefs in Dynamic Partially-Observed Visual Environments
In Advances in Neural Information Processing Systems
Accelerating Online Reinforcement Learning via Model-Based Meta-Learning
In Learning to Learn - Workshop at ICLR 2021
[Link]DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies
International Conference on Robotics and Automation (ICRA 2021)
arXiv [Link] Project PageFully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
In Conference on Robot Learning (CoRL)
VideoSMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
arXiv [Link] Project Page Video
2020
X2T: Training an X-to-Text Typing Interface with Online Learning from Implicit Feedback
International Conference on Learning Representations (ICLR) 2021
Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
International Conference on Robotics and Automation (ICRA 2021)
Ecological Reinforcement Learning
CoRR
[Link]Gamification of Crowd-Driven Environment Design
IEEE Computer Graphics and Applications
Morphology-Agnostic Visual Robotic Control
IEEE Robotics and Automation Letters
Deep Integration of Physical Humanoid Control and Crowd Navigation (\textbfbest paper runner up)
In Proceedings of the 13th International Conference on Motion in Games
2019
Contextual Imagined Goals for Self-Supervised Robotic Learning
In Conference on Robot Learning (CoRL)
arXiv Project Page VideoInteractive Architectural Design with Diverse Solution Exploration
IEEE Transactions on Visualization and Computer Graphics
Video
2018
Terrain RL Simulator
CoRR
[Link]Feedback Control For Cassie With Deep Reinforcement Learning
In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2018)
Model-Based Action Exploration for Learning Dynamic Motion Skills
In Proc. IEEE/RSJ Intl Conf on Intelligent Robots and Systems (IROS 2018)
VideoProgressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
International Conference on Learning Representations (ICLR) 2018
Video
2017
Evaluating and optimizing evacuation plans for crowd egress
IEEE computer graphics and applications
Perceptual Evaluation of Space in Virtual Environments
In Proceedings of the Tenth International Conference on Motion in Games
Crowd Sourced Co-design of Floor Plans Using Simulation Guided Games
In Proceedings of the Tenth International Conference on Motion in Games
On density flow relationships during crowd evacuation
Computer Animation and Virtual Worlds 28 (3-4)
DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning
SIGGRAPH 2017
Understanding spatial perception and visual modes in the review of architectural designs
In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 31
CODE: Crowd Optimized Design of Environments
Computer Animation and Virtual Worlds
2016
ACCLMesh: curvature-based navigation mesh generation
Computer Animation and Virtual Worlds
Terrain-adaptive locomotion skills using deep reinforcement learning
ACM Transactions on Graphics (TOG)
Using synthetic crowds to inform building pillar placements
In Virtual Humans and Crowds for Immersive Environments (VHCIE), IEEE
Towards Computer Assisted Crowd Aware Architectural Design
In CHI ’16 Extended Abstracts
[Link]
2015
Dynamic Terrain Traversal Skills Using Reinforcement Learning
ACM Trans. Graph.
[Link]Robust Space-Time Footsteps for Agent-Based Steering (best short paper)
Computer Animation and Virtual Worlds
VideoACCLMesh: Curvature-based Navigation Mesh Generation
In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games
[Link]Evaluating and Optimizing Level of Service for Crowd Evacuations
In Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games
[Link]
2014
Characterizing and Optimizing Game Level Difficulty
In Proceedings of the Seventh International Conference on Motion in Games
[Link]SteerFit: Automated Parameter Fitting for Steering Algorithms
In Eurographics/ ACM SIGGRAPH Symposium on Computer Animation
[Link]
2013
SteerPlex: Estimating Scenario Complexity for Simulated Crowds
In Proceedings of Motion on Games
[Link]