Sotabase

Career

· ML Lead, Cursor2024–
· Research Scientist, OpenAI2021–2024
· PhD Student, UC Berkeley2017–2022
· Research Assistant, UC Berkeley2013–2017

Publications (28)

GPT-4 Technical Report
2023
21,596
cited
Offline Reinforcement Learning with Implicit Q-Learning
International Conference on Learning Representations · 2021
1,237
cited
Overcoming Exploration in Reinforcement Learning with Demonstrations
IEEE International Conference on Robotics and Automation · 2017
857
cited
Accelerating Online Reinforcement Learning with Offline Datasets
arXiv.org · 2020
735
cited
Learning to Poke by Poking: Experiential Learning of Intuitive Physics
Neural Information Processing Systems · 2016
596
cited
Visual Reinforcement Learning with Imagined Goals
Neural Information Processing Systems · 2018
580
cited
Residual Reinforcement Learning for Robot Control
IEEE International Conference on Robotics and Automation · 2018
500
cited
Combining self-supervised learning and imitation for vision-based rope manipulation
IEEE International Conference on Robotics and Automation · 2017
326
cited
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
International Conference on Machine Learning · 2019
298
cited
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
IEEE/RJS International Conference on Intelligent RObots and Systems · 2019
209
cited
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
IEEE/RJS International Conference on Intelligent RObots and Systems · 2020
100
cited
Offline Meta-Reinforcement Learning with Online Self-Supervision
International Conference on Machine Learning · 2021
77
cited
Contextual Imagined Goals for Self-Supervised Robotic Learning
Conference on Robot Learning · 2019
74
cited
OpenAI GPT-5 System Card
2025
46
cited
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
Conference on Empirical Methods in Natural Language Processing · 2024
43
cited
Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
40
cited
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
International Conference on Machine Learning · 2022
38
cited
What Can I Do Here? Learning New Skills by Imagining Visual Affordances
IEEE International Conference on Robotics and Automation · 2021
36
cited
Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks
Conference on Robot Learning · 2022
32
cited
Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision
IEEE International Conference on Robotics and Automation · 2022
20
cited
Sotabase
Ashvin Nair | Researcher Profile | Sotabase | Sotabase