Sotabase

Career

· Assistant Professor, Carnegie Mellon University2024–
· Researcher, Google DeepMind2023–
· Research Intern, Google Brain2020–2023
· Master's Degree, Mechanical Engineering, Carnegie Mellon University2018–2020
· Doctor of Philosophy - PhD, Artificial Intelligence, University of California, Berkeley2018–2023
· PhD Student, University of California, Berkeley2018–2023
· Research Intern, Google Brain2017–
· Research Assistant, Indian Institute of Technology Bombay2017–2018
· B.Tech. with Honors in Computer Science and Engineering, Indian Institute of Technology Bombay2014–2018
· Research Intern, Institute of Science and Technology (IST), Austria

Publications (141)

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
arXiv.org · 2020
2,396
cited
Conservative Q-Learning for Offline Reinforcement Learning
Neural Information Processing Systems · 2020
2,259
cited
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
arXiv.org · 2020
1,639
cited
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
Neural Information Processing Systems · 2019
1,199
cited
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
arXiv.org · 2019
708
cited
COMBO: Conservative Offline Model-Based Policy Optimization
Neural Information Processing Systems · 2021
486
cited
Generative Verifiers: Reward Modeling as Next-Token Prediction
International Conference on Learning Representations · 2024
360
cited
Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models
International Conference on Learning Representations · 2023
244
cited
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Neural Information Processing Systems · 2023
195
cited
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
International Conference on Learning Representations · 2020
185
cited
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
International Conference on Machine Learning · 2024
176
cited
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
International Conference on Learning Representations · 2024
167
cited
Conservative Safety Critics for Exploration
International Conference on Learning Representations · 2020
156
cited
Diagnosing Bottlenecks in Deep Q-learning Algorithms
International Conference on Machine Learning · 2019
149
cited
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Neural Information Processing Systems · 2021
146
cited
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
International Conference on Learning Representations · 2020
142
cited
Role of Turmeric and Curcumin in Prevention and Treatment of Chronic Diseases: Lessons Learned from Clinical Trials.
ACS Pharmacology & Translational Science · 2023
136
cited
Pulsed electric field (PEF): Avant-garde extraction escalation technology in food industry
Trends in Food Science & Technology · 2022
134
cited
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Conference on Robot Learning · 2023
127
cited
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Neural Information Processing Systems · 2020
118
cited
Sotabase
Aviral Kumar | Researcher Profile | Sotabase | Sotabase