Archit Sharma

Most-cited papers

Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafael Rafailov, Archit Sharma, E. Mitchell, Stefano Ermon +2 more
2023Neural Information Processing Systems11K citations
Semantic Scholar
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Alexander Khazatsky, Karl Pertsch, S. Nair, Ashwin Balakrishna +96 more
2024Robotics: Science and Systems Conference1,268 citations
Semantic Scholar
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Katherine Tian, E. Mitchell, Allan Zhou, Archit Sharma +4 more
2023Conference on Empirical Methods in Natural Language Processing1,036 citations Open access
Semantic Scholar
Dynamics-Aware Unsupervised Discovery of Skills
Archit Sharma, Shi-Xiang Gu, S. Levine, Vikash Kumar +1 more
2019International Conference on Learning Representations523 citations
Semantic Scholar
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
Abigail O'Neill, Abdul Rehman, Abhiram Maddukuri, Abhishek Gupta +276 more
2024IEEE International Conference on Robotics and Automation283 citations
Semantic Scholar
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov +5 more
2024International Conference on Machine Learning210 citations
Semantic Scholar
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
Jian-Lan Luo, Zhe-Yuan Hu, Charles Xu, You-Liang Tan +6 more
2024IEEE International Conference on Robotics and Automation208 citations Open access
Semantic Scholar
Yell At Your Robot: Improving On-the-Fly from Language Corrections
L. Shi, Zhe-Yuan Hu, Tony Zhao, Archit Sharma +4 more
2024Robotics: Science and Systems Conference176 citations
Semantic Scholar
Waypoint-Based Imitation Learning for Robotic Manipulation
Lu Shi, Archit Sharma, Tony Zhao, Chelsea Finn
2023Conference on Robot Learning111 citations Open access
Semantic Scholar
Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, M. K. Srirama +3 more
2024arXiv.org99 citations
Semantic Scholar
Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning
Jing-Yun Yang, Max Sobol Mark, Brandon Vu, Archit Sharma +2 more
2023IEEE International Conference on Robotics and Automation76 citations Open access
Semantic Scholar
An Emulator for Fine-Tuning Large Language Models using Small Language Models
Eric Mitchell, Rafael Rafailov, Archit Sharma, Chelsea Finn +1 more
2023International Conference on Learning Representations76 citations
Semantic Scholar
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
Archit Sharma, Michael Ahn, S. Levine, Vikash Kumar +2 more
2020Robotics: Science and Systems Conference59 citations Open access
Semantic Scholar
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Archit Sharma, Sedrick Scott Keh, Eric Mitchell, Chelsea Finn +2 more
2024Neural Information Processing Systems50 citations
Semantic Scholar
Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning
Archit Sharma, Ahmed M. Ahmed, Rehaan Ahmad, Chelsea Finn
2023Conference on Robot Learning44 citations Open access
Semantic Scholar
Autonomous Reinforcement Learning: Formalism and Benchmarking
Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta +3 more
2021International Conference on Learning Representations44 citations
Semantic Scholar
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
Jongwook Choi, Archit Sharma, Honglak Lee, S. Levine +1 more
2021International Conference on Machine Learning43 citations
Semantic Scholar
Autonomous Reinforcement Learning via Subgoal Curricula
Archit Sharma, Abhishek Gupta, S. Levine, Karol Hausman +1 more
2021Neural Information Processing Systems42 citations
Semantic Scholar
You Only Live Once: Single-Life Reinforcement Learning
Annie S. Chen, Archit Sharma, S. Levine, Chelsea Finn
2022Neural Information Processing Systems33 citations Open access
Semantic Scholar
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Annie Xie, Fahim Tajwar, Archit Sharma, Chelsea Finn
2022Neural Information Processing Systems30 citations Open access
Semantic Scholar
Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning
Jongwook Choi, Archit Sharma, Honglak Lee, S. Levine +1 more
2021arXiv.org28 citations
Semantic Scholar
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
Archit Sharma, Rehaan Ahmad, Chelsea Finn
2022International Conference on Machine Learning27 citations Open access
Semantic Scholar
Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
Sheryl Hsu, Omar Khattab, Chelsea Finn, Archit Sharma
2024International Conference on Learning Representations26 citations
Semantic Scholar
Language Model Detectors Are Easily Optimized Against
Charlotte Nicks, Eric Mitchell, Rafael Rafailov, Archit Sharma +3 more
2024International Conference on Learning Representations25 citations
Semantic Scholar
RLVF: Learning from Verbal Feedback without Overgeneralization
Moritz Stephan, Alexander Khazatsky, Eric Mitchell, Annie S. Chen +3 more
2024International Conference on Machine Learning24 citations
Semantic Scholar
FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users
Anikait Singh, Sheryl Hsu, Kyle Hsu, Eric Mitchell +4 more
202522 citations
Semantic Scholar
Dynamics-Aware Unsupervised Skill Discovery
Archit Sharma, Shi-Xiang Gu, S. Levine, Vikash Kumar +1 more
2020International Conference on Learning Representations14 citations
Semantic Scholar
Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment
Annie S. Chen, Govind Chada, Laura M. Smith, Archit Sharma +3 more
2023arXiv.org13 citations
Semantic Scholar
Test-Time Alignment via Hypothesis Reweighting
Yoonho Lee, Jonathan Williams, H. Marklund, Archit Sharma +3 more
2024Trans. Mach. Learn. Res.12 citations
Semantic Scholar
A flexible probabilistic framework for large-margin mixture of experts
Archit Sharma, Siddhartha Saxena, Piyush Rai
2019Machine-mediated learning9 citations Open access
Semantic Scholar
Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias
Max Sobol Mark, Archit Sharma, Fahim Tajwar, Rafael Rafailov +2 more
2023arXiv.org8 citations Open access
Semantic Scholar
LLM Alignment via Reinforcement Learning from Multi-role Debates as Feedback
Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Jia-Qi Li +167 more
5 citations
Semantic Scholar
Discriminator Augmented Model-Based Reinforcement Learning
Behzad Haghgoo, Allan Zhou, Archit Sharma, Chelsea Finn
2021arXiv.org3 citations
Semantic Scholar
Persistent Reinforcement Learning via Subgoal Curricula
Archit Sharma, Abhishek Gupta, S. Levine, Karol Hausman +1 more
2021arXiv.org3 citations
Semantic Scholar
Steer, Don’t Solve: Training Small Critic Models for Large Code Agents
Shubham Gandhi, Yi-Qing Xie, Atharva Naik, Rui-Chen Zhu +74 more
0 citations
Semantic Scholar
Towards Proactive Personalization of LLMs through Profile Customization for Individual Users in Dialogues
Xiaotian Zhang, Yuan Wang, Rui-Zhe Chen, Ze-Ya Wang +75 more
0 citations
Semantic Scholar