Ashvin Nair

Most-cited papers

GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler, S. Agarwal +276 more
202328K citations
Semantic Scholar
Offline Reinforcement Learning with Implicit Q-Learning
Ilya Kostrikov, Ashvin Nair, S. Levine
2021International Conference on Learning Representations1,853 citations
Semantic Scholar
Accelerating Online Reinforcement Learning with Offline Datasets
Ashvin Nair, Murtaza Dalal, Abhishek Gupta, S. Levine
2020arXiv.org946 citations
Semantic Scholar
Overcoming Exploration in Reinforcement Learning with Demonstrations
Ashvin Nair, Bob McGrew, Marcin Andrychowicz, W. Zaremba +1 more
2017IEEE International Conference on Robotics and Automation921 citations Open access
Semantic Scholar
Residual Reinforcement Learning for Robot Control
T. Johannink, Shikhar Bahl, Ashvin Nair, Jianlan Luo +5 more
2018IEEE International Conference on Robotics and Automation759 citations Open access
Semantic Scholar
Learning to Poke by Poking: Experiential Learning of Intuitive Physics
Pulkit Agrawal, Ashvin Nair, P. Abbeel, Jitendra Malik +1 more
2016Neural Information Processing Systems634 citations
Semantic Scholar
Visual Reinforcement Learning with Imagined Goals
Ashvin Nair, Vitchyr H. Pong, Murtaza Dalal, Shikhar Bahl +2 more
2018Neural Information Processing Systems614 citations
Semantic Scholar
Combining self-supervised learning and imitation for vision-based rope manipulation
Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola +3 more
2017IEEE International Conference on Robotics and Automation345 citations Open access
Semantic Scholar
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
Vitchyr H. Pong, Murtaza Dalal, Steven Lin, Ashvin Nair +2 more
2019International Conference on Machine Learning323 citations
Semantic Scholar
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
Gerrit Schoettler, Ashvin Nair, Jianlan Luo, Shikhar Bahl +3 more
2019IEEE/RJS International Conference on Intelligent RObots and Systems226 citations Open access
Semantic Scholar
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, S. Levine +1 more
2020IEEE/RJS International Conference on Intelligent RObots and Systems111 citations Open access
Semantic Scholar
Offline Meta-Reinforcement Learning with Online Self-Supervision
Vitchyr H. Pong, Ashvin Nair, Laura M. Smith, Catherine Huang +1 more
2021International Conference on Machine Learning85 citations
Semantic Scholar
Contextual Imagined Goals for Self-Supervised Robotic Learning
Ashvin Nair, Shikhar Bahl, Alexander Khazatsky, Vitchyr H. Pong +2 more
2019Conference on Robot Learning77 citations
Semantic Scholar
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin +1 more
2022International Conference on Machine Learning53 citations Open access
Semantic Scholar
Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Kuan Fang, Patrick Yin, Ashvin Nair, S. Levine
2022IEEE/RJS International Conference on Intelligent RObots and Systems43 citations Open access
Semantic Scholar
What Can I Do Here? Learning New Skills by Imagining Visual Affordances
Alexander Khazatsky, Ashvin Nair, Daniel Jing, S. Levine
2021IEEE International Conference on Robotics and Automation37 citations Open access
Semantic Scholar
Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks
Kuan Fang, Patrick Yin, Ashvin Nair, H. Walke +2 more
2022Conference on Robot Learning34 citations Open access
Semantic Scholar
Composer 2 Technical Report
Aaron Chan, Ahmed Shalaby, Alexander Wettig, Aman Sanger +50 more
2026arXiv.org26 citations
Semantic Scholar
Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision
Ashvin Nair, Brian Zhu, Gokul Narayanan, Eugen Solowjow +1 more
2022IEEE International Conference on Robotics and Automation22 citations Open access
Semantic Scholar
DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies
Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair, Alexander Khazatsky +2 more
2021IEEE International Conference on Robotics and Automation15 citations Open access
Semantic Scholar
Scalable Robot Learning
Ashvin Nair
20220 citations
Semantic Scholar
SKEW-FIT: STATE-COVERING SELF-SUPERVISED RE-
Murtaza Dalal, Steven Lin, Ashvin Nair, Shikhar Bahl +1 more
20190 citations
Semantic Scholar