Sotabase

Career

· Assistant Professor, University of Toronto, Institute for Aerospace Studies2024–
· Researcher (implied from context), UC Berkeley

Publications (44)

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
IEEE International Conference on Computer Vision · 2019
398
cited
r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting
European Conference on Computer Vision · 2018
248
cited
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
International Conference on Machine Learning · 2020
217
cited
N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
International Conference on Learning Representations · 2017
177
cited
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
International Conference on Learning Representations · 2020
161
cited
Conservative Safety Critics for Exploration
International Conference on Learning Representations · 2020
156
cited
Deep Imitative Models for Flexible Inference, Planning, and Control
International Conference on Learning Representations · 2018
155
cited
First-Person Activity Forecasting with Online Inverse Reinforcement Learning
IEEE International Conference on Computer Vision · 2016
143
cited
ViNG: Learning Open-World Navigation with Visual Goals
IEEE International Conference on Robotics and Automation · 2020
121
cited
RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models
Conference on Robot Learning · 2021
117
cited
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
International Conference on Learning Representations · 2018
74
cited
Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting
Conference on Robot Learning · 2020
64
cited
Learning Action Maps of Large Environments via First-Person Vision
Computer Vision and Pattern Recognition · 2016
46
cited
Predictive-State Decoders: Encoding the Future into Recurrent Networks
Neural Information Processing Systems · 2017
43
cited
SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
International Conference on Learning Representations · 2021
42
cited
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
IEEE International Conference on Robotics and Automation · 2021
39
cited
Offline Reinforcement Learning for Visual Navigation
Conference on Robot Learning · 2022
38
cited
First-Person Activity Forecasting from Video with Online Inverse Reinforcement Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020
32
cited
Generative Hybrid Representations for Activity Forecasting With No-Regret Learning
Computer Vision and Pattern Recognition · 2019
32
cited
S2Net: Stochastic Sequential Pointcloud Forecasting
European Conference on Computer Vision · 2022
30
cited
Sotabase