Sotabase

Career

· Research Scientist, Google DeepMind2021–
· Research Intern, X The Moonshot Factory2019–2019
· PhD in Computer Science, UC Berkeley2016–2021
· Doctor of Philosophy (PhD) in Computer Science, University of California, Berkeley2016–2021
· Research Assistant, University of California, Berkeley2016–2021
· Research Intern, Virginia Tech2016–2016
· Research Intern, Cornell University2015–2015
· Bachelor of Technology in Electrical Engineering, Indian Institute of Technology, Kanpur2012–2016

Publications (29)

Visual Dialog
Computer Vision and Pattern Recognition · 2016
1,068
cited
End-to-End Robotic Reinforcement Learning without Reward Engineering
Robotics: Science and Systems · 2019
279
cited
Recurrent Neural Networks for driver activity anticipation via sensory-fusion architecture
IEEE International Conference on Robotics and Automation · 2015
272
cited
The Ingredients of Real-World Robotic Reinforcement Learning
International Conference on Learning Representations · 2020
195
cited
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
International Conference on Learning Representations · 2020
161
cited
Brain4Cars: Car That Knows Before You Do via Sensory-Fusion Deep Learning Architecture
arXiv.org · 2016
137
cited
Divide-and-Conquer Reinforcement Learning
International Conference on Learning Representations · 2017
131
cited
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition
Neural Information Processing Systems · 2018
130
cited
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
arXiv.org · 2020
110
cited
Few-Shot Goal Inference for Visuomotor Learning and Planning
Conference on Robot Learning · 2018
72
cited
Improving Large Language Model Fine-tuning for Solving Math Problems
arXiv.org · 2023
66
cited
i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops
Conference on Robot Learning · 2022
66
cited
Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning
Conference on Robot Learning · 2022
37
cited
Scalable Multi-Task Imitation Learning with Autonomous Improvement
IEEE International Conference on Robotics and Automation · 2020
37
cited
Robotic Table Tennis: A Case Study into a High Speed Learning System
Robotics: Science and Systems · 2023
24
cited
GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images
IEEE International Conference on Computer Vision · 2017
23
cited
Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
IEEE International Conference on Robotics and Automation · 2022
13
cited
Deep Learning for Visual Question Answering
2015
3
cited
Chaining Behaviors from Data with Model-Free Reinforcement Learning
Conference on Robot Learning · 2020
2
cited
6-DOF Monocular Relocalization with Convolutional Neural Networks
2016
1
cited
Sotabase
Avi Singh | Researcher Profile | Sotabase | Sotabase