Pulkit Agrawal

204 papers A* 58A 4B 3Misc 13Journal 110Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Agile asymmetric multi-legged locomotion: contact planning via geometric mechanics and spin model duality. CoRR Jackson Habala, Gabriel B. Margolis, Tianyu Wang, Pratyush Bhatt, Juntao He, Naheel Naeem, Zhaochen Xu, Pulkit Agrawal, Daniel I. Goldman, Di Luo, Baxi Chong
2026	J	`jnl`	Self-Distillation Enables Continual Learning. CoRR Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal
2026	J	`jnl`	Training Language Models via Neural Cellular Automata. CoRR Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal
2025	J	`jnl`	A distributional reinforcement learning model for optimal glucose control after cardiac surgery. npj Digit. Medicine Jacob Desman, Zhang-Wei Hong, Moein Sabounchi, Ashwin S. Sawant, Jaskirat Gill, Ana C. Costa, Gagan Kumar, Rajeev Sharma, Arpeta Gupta, Paul McCarthy, Veena Nandwani, Doug Powell, Alexandra Carideo, Donnie Goodwin, Sanam Ahmed, Umesh Gidwani, Matthew A. Levin, Robin Varghese, Farzan Filsoufi, Robert Freeman, Avniel Shetreat-Klein, Alexander W. Charney, Ira S. Hofer, Lili Chan, David Reich, Patricia H. Kovatch, Roopa Kohli-Seth, Monica Kraft, Pulkit Agrawal, John A. Kellum, Girish N. Nadkarni, Ankit Sakhuja
2025	J	`jnl`	Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation. CoRR Nolan Fey, Gabriel B. Margolis, Martin Peticco, Pulkit Agrawal
2025	A*	`conf`	DART: Dexterous Augmented Reality Teleoperation Platform for Large-Scale Robot Data Collection in Simulation. ICRA Younghyo Park, Jagdeep Singh Bhatia, Lars Ankile, Pulkit Agrawal
2025	J	`jnl`	DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation. CoRR Haoshu Fang, Branden Romero, Yichen Xie, Arthur Hu, Bo-Ruei Huang, Juan Alvarez, Matthew Kim, Gabriel B. Margolis, Kavya Anbarasu, Masayoshi Tomizuka, Edward H. Adelson, Pulkit Agrawal
2025	J	`jnl`	DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation. CoRR Martin Peticco, Gabriella Ulloa, John Marangola, Pulkit Agrawal
2025	A*	`conf`	Diffusion Policy Policy Optimization. ICLR Allen Z. Ren, Justin Lidard, Lars Lien Ankile, Anthony Simeonov, Pulkit Agrawal, Anirudha Majumdar, Benjamin Burchfiel, Hongkai Dai, Max Simchowitz
2025	A*	`conf`	Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning. ICLR Moritz Reuss, Jyothish Pari, Pulkit Agrawal, Rudolf Lioutikov
2025	A*	`conf`	Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective. ICML Seungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal
2025	A*	`conf`	From Imitation to Refinement - Residual Rl for Precise Assembly. ICRA Lars Ankile, Anthony Simeonov, Idan Shenfeld, Marcel Torne, Pulkit Agrawal
2025	J	`jnl`	General Reasoning Requires Learning to Reason from the Get-go. CoRR Seungwook Han, Jyothish Pari, Samuel J. Gershman, Pulkit Agrawal
2025	J	`jnl`	Going Beyond Heuristics by Imposing Policy Improvement as a Constraint. CoRR Chi-Chang Lee, Zhang-Wei Hong, Pulkit Agrawal
2025	—	`conf`	Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning. RoboSoft Yi-Hsuan Hsiao, Wei-Tung Chen, Yun-Sheng Chang, Pulkit Agrawal, YuFeng Chen
2025	J	`jnl`	Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning. CoRR Yi-Hsuan Hsiao, Wei-Tung Chen, Yun-Sheng Chang, Pulkit Agrawal, YuFeng Chen
2025	J	`jnl`	Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules. CoRR Nofit Segal, Aviv Netanyahu, Kevin P. Greenman, Pulkit Agrawal, Rafael Gómez-Bombarelli
2025	J	`jnl`	Language Model Personalization via Reward Factorization. CoRR Idan Shenfeld, Felix Faltings, Pulkit Agrawal, Aldo Pacchiano
2025	A*	`conf`	ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization. ICLR Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano, Pulkit Agrawal
2025	—	`conf`	Position: General Intelligence Requires Reward-based Pretraining. ICML (Position Papers) Seungwook Han, Jyothish Pari, Samuel J. Gershman, Pulkit Agrawal
2025	J	`jnl`	RL's Razor: Why Online Reinforcement Learning Forgets Less. CoRR Idan Shenfeld, Jyothish Pari, Pulkit Agrawal
2025	J	`jnl`	Self-Adapting Language Models. CoRR Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek, Yoon Kim, Pulkit Agrawal
2025	J	`jnl`	SoftMimic: Learning Compliant Whole-body Control from Examples. CoRR Gabriel B. Margolis, Michelle Wang, Nolan Fey, Pulkit Agrawal
2025	A*	`conf`	Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation. ICRA Tao Chen, Eric Cousineau, Naveen Kuppuswamy, Pulkit Agrawal
2024	Misc	`conf`	Action Space Design in Reinforcement Learning for Robot Motor Skills. CoRL Julian Eßer, Gabriel B. Margolis, Oliver Urbann, Sören Kerner, Pulkit Agrawal
2024	A*	`conf`	Aligning Human and Robot Representations. HRI Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie A. Shah, Anca D. Dragan
2024	J	`jnl`	Automatic Environment Shaping is the Next Frontier in RL. CoRR Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal
2024	J	`jnl`	Collective Model Intelligence Requires Compatible Specialization. CoRR Jyothish Pari, Samy Jelassi, Pulkit Agrawal
2024	Misc	`ed.`	Conference on Robot Learning, 6-9 November 2024, Munich, Germany. CoRL Pulkit Agrawal, Oliver Kroemer, Wolfram Burgard
2024	A*	`conf`	Curiosity-driven Red-teaming for Large Language Models. ICLR Zhang-Wei Hong, Idan Shenfeld, Tsun-Hsuan Wang, Yung-Sung Chuang, Aldo Pareja, James R. Glass, Akash Srivastava, Pulkit Agrawal
2024	J	`jnl`	Curiosity-driven Red-teaming for Large Language Models. CoRR Zhang-Wei Hong, Idan Shenfeld, Tsun-Hsuan Wang, Yung-Sung Chuang, Aldo Pareja, James R. Glass, Akash Srivastava, Pulkit Agrawal
2024	J	`jnl`	DexHub and DART: Towards Internet Scale Robot Data Collection. CoRR Younghyo Park, Jagdeep Singh Bhatia, Lars Ankile, Pulkit Agrawal
2024	J	`jnl`	Diffusion Policy Policy Optimization. CoRR Allen Z. Ren, Justin Lidard, Lars Ankile, Anthony Simeonov, Pulkit Agrawal, Anirudha Majumdar, Benjamin Burchfiel, Hongkai Dai, Max Simchowitz
2024	J	`jnl`	Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning. CoRR Moritz Reuss, Jyothish Pari, Pulkit Agrawal, Rudolf Lioutikov
2024	J	`jnl`	Embodied Red Teaming for Auditing Robotic Foundation Models. CoRR Sathwik Karnik, Zhang-Wei Hong, Nishant Abhangi, Yen-Chen Lin, Tsun-Hsuan Wang, Pulkit Agrawal
2024	J	`jnl`	Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers. CoRR Seungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal
2024	J	`jnl`	Everyday Finger: A Robotic Finger that Meets the Needs of Everyday Interactive Manipulation. CoRR Rubén Castro Ornelas, Tomás Cantú, Isabel Sperandio, Alexander H. Slocum, Pulkit Agrawal
2024	A*	`conf`	Everyday finger: a robotic finger that meets the needs of everyday interactive manipulation. ICRA Rubén Castro Ornelas, Tomás Cantú, Isabel Sperandio, Alexander H. Slocum, Pulkit Agrawal
2024	A	`conf`	EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation. IROS Branden Romero, Haoshu Fang, Pulkit Agrawal, Edward H. Adelson
2024	J	`jnl`	EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation. CoRR Branden Romero, Haoshu Fang, Pulkit Agrawal, Edward H. Adelson
2024	A*	`conf`	Few-Shot Task Learning through Inverse Generative Modeling. NeurIPS Aviv Netanyahu, Yilun Du, Antonia Bronars, Jyothish Pari, Josh Tenenbaum, Tianmin Shu, Pulkit Agrawal
2024	J	`jnl`	Few-Shot Task Learning through Inverse Generative Modeling. CoRR Aviv Netanyahu, Yilun Du, Antonia Bronars, Jyothish Pari, Joshua B. Tenenbaum, Tianmin Shu, Pulkit Agrawal
2024	J	`jnl`	From Imitation to Refinement - Residual RL for Precise Visual Assembly. CoRR Lars Ankile, Anthony Simeonov, Idan Shenfeld, Marcel Torne, Pulkit Agrawal
2024	A*	`conf`	Going Beyond Heuristics by Imposing Policy Improvement as a Constraint. NeurIPS Chi-Chang Lee, Zhang-Wei Hong, Pulkit Agrawal
2024	J	`jnl`	Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building. Trans. Mach. Learn. Res. Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila R. Fiete
2024	J	`jnl`	ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning. CoRR Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
2024	A	`conf`	JUICER: Data-Efficient Imitation Learning for Robotic Assembly. IROS Lars Ankile, Anthony Simeonov, Idan Shenfeld, Pulkit Agrawal
2024	J	`jnl`	JUICER: Data-Efficient Imitation Learning for Robotic Assembly. CoRR Lars Ankile, Anthony Simeonov, Idan Shenfeld, Pulkit Agrawal
2024	A*	`conf`	Learning Force Control for Legged Manipulation. ICRA Tifanny Portela, Gabriel B. Margolis, Yandong Ji, Pulkit Agrawal
2024	J	`jnl`	Learning Force Control for Legged Manipulation. CoRR Tifanny Portela, Gabriel B. Margolis, Yandong Ji, Pulkit Agrawal
2024	A*	`conf`	Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient. NeurIPS Steven Li, Rickmer Krohn, Tao Chen, Anurag Ajay, Pulkit Agrawal, Georgia Chalvatzaki
2024	J	`jnl`	Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient. CoRR Zechu Li, Rickmer Krohn, Tao Chen, Anurag Ajay, Pulkit Agrawal, Georgia Chalvatzaki
2024	J	`jnl`	Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck. CoRR Bipasha Sen, Michelle Wang, Nandini Thakur, Aditya Agarwal, Pulkit Agrawal
2024	A*	`conf`	Lifelong Robot Learning with Human Assisted Language Planners. ICRA Meenal Parakh, Alisha Fong, Anthony Simeonov, Tao Chen, Abhishek Gupta, Pulkit Agrawal
2024	A*	`conf`	Maximizing Quadruped Velocity by Minimizing Energy. ICRA Srinath Mahankali, Chi-Chang Lee, Gabriel B. Margolis, Zhang-Wei Hong, Pulkit Agrawal
2024	J	`jnl`	ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization. CoRR Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano, Pulkit Agrawal
2024	A*	`conf`	OpenEQA: Embodied Question Answering in the Era of Foundation Models. CVPR Arjun Majumdar, Anurag Ajay, Xiaohan Zhang, Pranav Putta, Sriram Yenamandra, Mikael Henaff, Sneha Silwal, Paul McVay, Oleksandr Maksymets, Sergio Arnaud, Karmesh Yadav, Qiyang Li, Ben Newman, Mohit Sharma, Vincent-Pierre Berges, Shiqi Zhang, Pulkit Agrawal, Yonatan Bisk, Dhruv Batra, Mrinal Kalakrishnan, Franziska Meier, Chris Paxton, Alexander Sax, Aravind Rajeswaran
2024	A*	`conf`	Position: Automatic Environment Shaping is the Next Frontier in RL. ICML Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal
2024	J	`jnl`	ROER: Regularized Optimal Experience Replay. RLJ Changling Li, Zhang-Wei Hong, Pulkit Agrawal, Divyansh Garg, Joni Pajarinen
2024	J	`jnl`	ROER: Regularized Optimal Experience Replay. CoRR Changling Li, Zhang-Wei Hong, Pulkit Agrawal, Divyansh Garg, Joni Pajarinen
2024	A*	`conf`	Random Latent Exploration for Deep Reinforcement Learning. ICML Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal
2024	J	`jnl`	Random Latent Exploration for Deep Reinforcement Learning. CoRR Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal
2024	A*	`conf`	Rank2Reward: Learning Shaped Reward Functions from Passive Video. ICRA Daniel Yang, Davin Tjia, Jacob Berg, Dima Damen, Pulkit Agrawal, Abhishek Gupta
2024	J	`jnl`	Rank2Reward: Learning Shaped Reward Functions from Passive Video. CoRR Daniel Yang, Davin Tjia, Jacob Berg, Dima Damen, Pulkit Agrawal, Abhishek Gupta
2024	J	`jnl`	Rapid locomotion via reinforcement learning. Int. J. Robotics Res. Gabriel B. Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal
2024	—	`conf`	Reconciling Reality through Simulation: A Real-To-Sim-to-Real Approach for Robust Manipulation. Robotics: Science and Systems Marcel Torne Villasevil, Anthony Simeonov, Zechu Li, April Chan, Tao Chen, Abhishek Gupta, Pulkit Agrawal
2024	J	`jnl`	Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation. CoRR Marcel Torne, Anthony Simeonov, Zechu Li, April Chan, Tao Chen, Abhishek Gupta, Pulkit Agrawal
2024	J	`jnl`	Robot Learning with Super-Linear Scaling. CoRR Marcel Torne, Arhan Jain, Jiayi Yuan, Vidaaranya Macha, Lars Ankile, Anthony Simeonov, Pulkit Agrawal, Abhishek Gupta
2024	J	`jnl`	Training Neural Networks from Scratch with Parallel Low-Rank Adapters. CoRR Minyoung Huh, Brian Cheung, Jeremy Bernstein, Phillip Isola, Pulkit Agrawal
2024	J	`jnl`	Value Augmented Sampling for Language Model Alignment and Personalization. CoRR Seungwook Han, Idan Shenfeld, Akash Srivastava, Yoon Kim, Pulkit Agrawal
2024	J	`jnl`	Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation. CoRR Tao Chen, Eric Cousineau, Naveen Kuppuswamy, Pulkit Agrawal
2023	J	`jnl`	Aligning Robot and Human Representations. CoRR Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie Shah, Anca D. Dragan
2023	Misc	`conf`	Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback. CoRL Max Balsells, Marcel Torne Villasevil, Zihan Wang, Samedh Desai, Pulkit Agrawal, Abhishek Gupta
2023	J	`jnl`	Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback. CoRR Max Balsells, Marcel Torne, Zihan Wang, Samedh Desai, Pulkit Agrawal, Abhishek Gupta
2023	A*	`conf`	Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. NeurIPS Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. CoRR Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback. CoRR Marcel Torne, Max Balsells, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal, Abhishek Gupta
2023	A*	`conf`	Breadcrumbs to the Goal: Supervised Goal Selection from Human-in-the-Loop Feedback. NeurIPS Marcel Torne Villasevil, Max Balsells, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal, Abhishek Gupta
2023	A*	`conf`	Compositional Foundation Models for Hierarchical Planning. NeurIPS Anurag Ajay, Seungwook Han, Yilun Du, Shuang Li, Abhi Gupta, Tommi S. Jaakkola, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Akash Srivastava, Pulkit Agrawal
2023	J	`jnl`	Compositional Foundation Models for Hierarchical Planning. CoRR Anurag Ajay, Seungwook Han, Yilun Du, Shuang Li, Abhi Gupta, Tommi S. Jaakkola, Josh Tenenbaum, Leslie Pack Kaelbling, Akash Srivastava, Pulkit Agrawal
2023	J	`jnl`	Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies. CoRR Ligong Han, Seungwook Han, Shivchander Sudalairaj, Charlotte Loh, Rumen Dangovski, Fei Deng, Pulkit Agrawal, Dimitris N. Metaxas, Leonid Karlinsky, Tsui-Wei Weng, Akash Srivastava
2023	A*	`conf`	Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation. ICML Andi Peng, Aviv Netanyahu, Mark K. Ho, Tianmin Shu, Andreea Bobu, Julie Shah, Pulkit Agrawal
2023	J	`jnl`	Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation. CoRR Andi Peng, Aviv Netanyahu, Mark K. Ho, Tianmin Shu, Andreea Bobu, Julie Shah, Pulkit Agrawal
2023	A*	`conf`	DribbleBot: Dynamic Legged Manipulation in the Wild. ICRA Yandong Ji, Gabriel B. Margolis, Pulkit Agrawal
2023	J	`jnl`	DribbleBot: Dynamic Legged Manipulation in the Wild. CoRR Yandong Ji, Gabriel B. Margolis, Pulkit Agrawal
2023	J	`jnl`	Geometry of contact: contact planning for multi-legged robots via spin models duality. CoRR Baxi Chong, Di Luo, Tianyu Wang, Gabriel B. Margolis, Juntao He, Pulkit Agrawal, Marin Soljacic, Daniel I. Goldman
2023	A*	`conf`	Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting. ICLR Zhang-Wei Hong, Pulkit Agrawal, Remi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting. CoRR Zhang-Wei Hong, Pulkit Agrawal, Rémi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Human-Assisted Continual Robot Learning with Foundation Models. CoRR Meenal Parakh, Alisha Fong, Anthony Simeonov, Abhishek Gupta, Tao Chen, Pulkit Agrawal
2023	A*	`conf`	Human-Guided Complexity-Controlled Abstractions. NeurIPS Andi Peng, Mycal Tucker, Eoin M. Kenny, Noga Zaslavsky, Pulkit Agrawal, Julie A. Shah
2023	J	`jnl`	Human-Guided Complexity-Controlled Abstractions. CoRR Andi Peng, Mycal Tucker, Eoin M. Kenny, Noga Zaslavsky, Pulkit Agrawal, Julie Shah
2023	A*	`conf`	Is Conditional Generative Modeling all you need for Decision Making? ICLR Anurag Ajay, Yilun Du, Abhi Gupta, Joshua B. Tenenbaum, Tommi S. Jaakkola, Pulkit Agrawal
2023	A*	`conf`	Learning to Extrapolate: A Transductive Approach. ICLR Aviv Netanyahu, Abhishek Gupta, Max Simchowitz, Kaiqing Zhang, Pulkit Agrawal
2023	J	`jnl`	Learning to Extrapolate: A Transductive Approach. CoRR Aviv Netanyahu, Abhishek Gupta, Max Simchowitz, Kaiqing Zhang, Pulkit Agrawal
2023	Misc	`conf`	Learning to See Physical Properties with Active Sensing Motor Policies. CoRL Gabriel B. Margolis, Xiang Fu, Yandong Ji, Pulkit Agrawal
2023	J	`jnl`	Learning to See Physical Properties with Active Sensing Motor Policies. CoRR Gabriel B. Margolis, Xiang Fu, Yandong Ji, Pulkit Agrawal
2023	J	`jnl`	Neuro-Inspired Efficient Map Building via Fragmentation and Recall. CoRR Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
2023	J	`jnl`	Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity. CoRR Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
2023	A*	`conf`	Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation. ICML Zechu Li, Tao Chen, Zhang-Wei Hong, Anurag Ajay, Pulkit Agrawal
2023	J	`jnl`	Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation. CoRR Zechu Li, Tao Chen, Zhang-Wei Hong, Anurag Ajay, Pulkit Agrawal
2023	A*	`conf`	Self-Supervised Reinforcement Learning that Transfers using Random Features. NeurIPS Boyuan Chen, Chuning Zhu, Pulkit Agrawal, Kaiqing Zhang, Abhishek Gupta
2023	J	`jnl`	Self-Supervised Reinforcement Learning that Transfers using Random Features. CoRR Boyuan Chen, Chuning Zhu, Pulkit Agrawal, Kaiqing Zhang, Abhishek Gupta
2023	Misc	`conf`	Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement. CoRL Anthony Simeonov, Ankit Goyal, Lucas Manuelli, Yen-Chen Lin, Alina Sarmiento, Alberto Rodriguez Garcia, Pulkit Agrawal, Dieter Fox
2023	J	`jnl`	Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement. CoRR Anthony Simeonov, Ankit Goyal, Lucas Manuelli, Yen-Chen Lin, Alina Sarmiento, Alberto Rodriguez, Pulkit Agrawal, Dieter Fox
2023	A*	`conf`	Statistical Learning under Heterogenous Distribution Shift. ICML Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
2023	J	`jnl`	Statistical Learning under Heterogenous Distribution Shift. CoRR Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
2023	A*	`conf`	Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks. ICML Minyoung Huh, Brian Cheung, Pulkit Agrawal, Phillip Isola
2023	J	`jnl`	Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks. CoRR Minyoung Huh, Brian Cheung, Pulkit Agrawal, Phillip Isola
2023	A*	`conf`	TGRL: An Algorithm for Teacher Guided Reinforcement Learning. ICML Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar, Pulkit Agrawal
2023	J	`jnl`	TGRL: An Algorithm for Teacher Guided Reinforcement Learning. CoRR Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar, Pulkit Agrawal
2023	A*	`conf`	TactoFind: A Tactile Only System for Object Retrieval. ICRA Sameer Pai, Tao Chen, Megha Tippur, Edward H. Adelson, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	TactoFind: A Tactile Only System for Object Retrieval. CoRR Sameer Pai, Tao Chen, Megha Tippur, Edward H. Adelson, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	The Low-Rank Simplicity Bias in Deep Networks. Trans. Mach. Learn. Res. Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola
2023	A	`conf`	Visual Pre-Training for Navigation: What Can We Learn from Noise? IROS Yanwei Wang, Ching-Yun Ko, Pulkit Agrawal
2023	J	`jnl`	Visual dexterity: In-hand reorientation of novel and complex object shapes. Sci. Robotics Tao Chen, Megha Tippur, Siyang Wu, Vikash Kumar, Edward H. Adelson, Pulkit Agrawal
2022	A*	`conf`	An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators. ICRA Lara Zlokapa, Yiyue Luo, Jie Xu, Michael Foshey, Kui Wu, Pulkit Agrawal, Wojciech Matusik
2022	J	`jnl`	An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators. CoRR Lara Zlokapa, Yiyue Luo, Jie Xu, Michael Foshey, Kui Wu, Pulkit Agrawal, Wojciech Matusik
2022	A*	`conf`	Bi-linear Value Networks for Multi-goal Reinforcement Learning. ICLR Zhang-Wei Hong, Ge Yang, Pulkit Agrawal
2022	J	`jnl`	Bilinear value networks. CoRR Zhang-Wei Hong, Ge Yang, Pulkit Agrawal
2022	A*	`conf`	Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning. ICML Aviv Netanyahu, Tianmin Shu, Joshua B. Tenenbaum, Pulkit Agrawal
2022	J	`jnl`	Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning. CoRR Aviv Netanyahu, Tianmin Shu, Joshua B. Tenenbaum, Pulkit Agrawal
2022	A*	`conf`	Distributionally Adaptive Meta Reinforcement Learning. NeurIPS Anurag Ajay, Abhishek Gupta, Dibya Ghosh, Sergey Levine, Pulkit Agrawal
2022	J	`jnl`	Distributionally Adaptive Meta Reinforcement Learning. CoRR Anurag Ajay, Abhishek Gupta, Dibya Ghosh, Sergey Levine, Pulkit Agrawal
2022	Misc	`conf`	Efficient Tactile Simulation with Differentiability for Robotic Manipulation. CoRL Jie Xu, Sangwoon Kim, Tao Chen, Alberto Rodriguez Garcia, Pulkit Agrawal, Wojciech Matusik, Shinjiro Sueda
2022	A*	`conf`	Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations. ICLR Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljacic
2022	J	`jnl`	Is Conditional Generative Modeling all you need for Decision-Making? CoRR Anurag Ajay, Yilun Du, Abhi Gupta, Joshua B. Tenenbaum, Tommi S. Jaakkola, Pulkit Agrawal
2022	A*	`conf`	Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation. ICRA Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann
2022	A*	`conf`	Offline RL Policies Should Be Trained to be Adaptive. ICML Dibya Ghosh, Anurag Ajay, Pulkit Agrawal, Sergey Levine
2022	J	`jnl`	Offline RL Policies Should be Trained to be Adaptive. CoRR Dibya Ghosh, Anurag Ajay, Pulkit Agrawal, Sergey Levine
2022	A*	`conf`	Overcoming The Spectral Bias of Neural Value Approximation. ICLR Ge Yang, Anurag Ajay, Pulkit Agrawal
2022	J	`jnl`	Overcoming the Spectral Bias of Neural Value Approximation. CoRR Ge Yang, Anurag Ajay, Pulkit Agrawal
2022	—	`conf`	Rapid Locomotion via Reinforcement Learning. Robotics: Science and Systems Gabriel B. Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal
2022	J	`jnl`	Rapid Locomotion via Reinforcement Learning. CoRR Gabriel B. Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal
2022	J	`jnl`	Redeeming Intrinsic Rewards via Constrained Optimization. CoRR Eric Chen, Zhang-Wei Hong, Joni Pajarinen, Pulkit Agrawal
2022	A*	`conf`	Redeeming intrinsic rewards via constrained optimization. NeurIPS Eric Chen, Zhang-Wei Hong, Joni Pajarinen, Pulkit Agrawal
2022	Misc	`conf`	SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields. CoRL Anthony Simeonov, Yilun Du, Yen-Chen Lin, Alberto Rodriguez Garcia, Leslie Pack Kaelbling, Tomás Lozano-Pérez, Pulkit Agrawal
2022	J	`jnl`	SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields. CoRR Anthony Simeonov, Yilun Du, Yen-Chen Lin, Alberto Rodriguez, Leslie Pack Kaelbling, Tomás Lozano-Pérez, Pulkit Agrawal
2022	A*	`conf`	Stable Object Reorientation using Contact Plane Registration. ICRA Richard Li, Carlos Esteves, Ameesh Makadia, Pulkit Agrawal
2022	J	`jnl`	Stable Object Reorientation using Contact Plane Registration. CoRR Richard Li, Carlos Esteves, Ameesh Makadia, Pulkit Agrawal
2022	A	`conf`	Stubborn: A Strong Baseline for Indoor Object Navigation. IROS Haokuan Luo, Albert Yue, Zhang-Wei Hong, Pulkit Agrawal
2022	J	`jnl`	Stubborn: A Strong Baseline for Indoor Object Navigation. CoRR Haokuan Luo, Albert Yue, Zhang-Wei Hong, Pulkit Agrawal
2022	A*	`conf`	Topological Experience Replay. ICLR Zhang-Wei Hong, Tao Chen, Yen-Chen Lin, Joni Pajarinen, Pulkit Agrawal
2022	J	`jnl`	Topological Experience Replay. CoRR Zhang-Wei Hong, Tao Chen, Yen-Chen Lin, Joni Pajarinen, Pulkit Agrawal
2022	J	`jnl`	Visual Dexterity: In-hand Dexterous Manipulation from Depth. CoRR Tao Chen, Megha Tippur, Siyang Wu, Vikash Kumar, Edward H. Adelson, Pulkit Agrawal
2022	Misc	`conf`	Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior. CoRL Gabriel B. Margolis, Pulkit Agrawal
2022	J	`jnl`	Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior. CoRR Gabriel B. Margolis, Pulkit Agrawal
2021	Misc	`conf`	3D Neural Scene Representations for Visuomotor Control. CoRL Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba
2021	J	`jnl`	3D Neural Scene Representations for Visuomotor Control. CoRR Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba
2021	Misc	`conf`	A System for General In-Hand Object Re-Orientation. CoRL Tao Chen, Jie Xu, Pulkit Agrawal
2021	J	`jnl`	A System for General In-Hand Object Re-Orientation. CoRR Tao Chen, Jie Xu, Pulkit Agrawal
2021	—	`conf`	Adapting Deep Learning Models to New Meteorological Contexts Using Transfer Learning. IEEE BigData Pooya Khorrami, Olga Simek, Brian Cheung, Mark Veillette, Rumen Dangovski, Ileana Rugina, Marin Soljacic, Pulkit Agrawal
2021	—	`conf`	An End-to-End Differentiable Framework for Contact-Aware Robot Design. Robotics: Science and Systems Jie Xu, Tao Chen, Lara Zlokapa, Michael Foshey, Wojciech Matusik, Shinjiro Sueda, Pulkit Agrawal
2021	J	`jnl`	An End-to-End Differentiable Framework for Contact-Aware Robot Design. CoRR Jie Xu, Tao Chen, Lara Zlokapa, Michael Foshey, Wojciech Matusik, Shinjiro Sueda, Pulkit Agrawal
2021	J	`jnl`	Equivariant Contrastive Learning. CoRR Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljacic
2021	A*	`conf`	Learning Task Informed Abstractions. ICML Xiang Fu, Ge Yang, Pulkit Agrawal, Tommi S. Jaakkola
2021	J	`jnl`	Learning Task Informed Abstractions. CoRR Xiang Fu, Ge Yang, Pulkit Agrawal, Tommi S. Jaakkola
2021	Misc	`conf`	Learning to Jump from Pixels. CoRL Gabriel B. Margolis, Tao Chen, Kartik Paigwar, Xiang Fu, Donghyun Kim, Sangbae Kim, Pulkit Agrawal
2021	J	`jnl`	Learning to Jump from Pixels. CoRR Gabriel B. Margolis, Tao Chen, Kartik Paigwar, Xiang Fu, Donghyun Kim, Sangbae Kim, Pulkit Agrawal
2021	J	`jnl`	Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation. CoRR Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann
2021	A*	`conf`	OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. ICLR Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum
2021	A*	`conf`	Residual Model Learning for Microrobot Control. ICRA Joshua Gruenstein, Tao Chen, Neel Doshi, Pulkit Agrawal
2021	J	`jnl`	Residual Model Learning for Microrobot Control. CoRR Joshua Gruenstein, Tao Chen, Neel Doshi, Pulkit Agrawal
2021	J	`jnl`	The Low-Rank Simplicity Bias in Deep Networks. CoRR Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola
2021	Misc	`conf`	The Task Specification Problem. CoRL Pulkit Agrawal
2020	Misc	`conf`	A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects. CoRL Anthony Simeonov, Yilun Du, Beomjoon Kim, Francois Robert Hogan, Joshua B. Tenenbaum, Pulkit Agrawal, Alberto Rodriguez
2020	J	`jnl`	A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects. CoRR Anthony Simeonov, Yilun Du, Beomjoon Kim, Francois Robert Hogan, Joshua B. Tenenbaum, Pulkit Agrawal, Alberto Rodriguez
2020	B	`conf`	Exploring Exploration: Comparing Children with Agents in Unified Exploration Environments. CogSci Eliza Kosoy, Jasmine Collins, David M. Chan, Deepak Pathak, Pulkit Agrawal, Alison Gopnik
2020	J	`jnl`	OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. CoRR Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum
2020	A*	`conf`	Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning. ICRA Richard Li, Allan Jabri, Trevor Darrell, Pulkit Agrawal
2019	B	`conf`	Curiouser and Curiouser: Children's intrinsic exploration of mazes and its effects on reaching a goal. CogSci Eliza Kosoy, Deepak Pathak, Pulkit Agrawal, Alison Gopnik
2019	B	`conf`	Human-level but not human-like: Deep Reinforcement Learning in the dark. CogSci Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Alyosha A. Efros, Tom Griffiths
2019	A*	`conf`	Superposition of many models into one. NeurIPS Brian Cheung, Alexander Terekhov, Yubei Chen, Pulkit Agrawal, Bruno A. Olshausen
2019	J	`jnl`	Superposition of many models into one. CoRR Brian Cheung, Alexander Terekhov, Yubei Chen, Pulkit Agrawal, Bruno A. Olshausen
2019	J	`jnl`	Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning. CoRR Richard Li, Allan Jabri, Trevor Darrell, Pulkit Agrawal
2018	—	`—`	Computational Sensorimotor Learning. Pulkit Agrawal
2018	—	`conf`	Investigating Human Priors for Playing Video Games. ICLR (Workshop) Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Alyosha A. Efros, Thomas L. Griffiths
2018	A*	`conf`	Investigating Human Priors for Playing Video Games. ICML Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Tom Griffiths, Alexei A. Efros
2018	J	`jnl`	Investigating Human Priors for Playing Video Games. CoRR Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Thomas L. Griffiths, Alexei A. Efros
2018	—	`conf`	Learning Instance Segmentation by Interaction. CVPR Workshops Deepak Pathak, Yide Shentu, Dian Chen, Pulkit Agrawal, Trevor Darrell, Sergey Levine, Jitendra Malik
2018	J	`jnl`	Learning Instance Segmentation by Interaction. CoRR Deepak Pathak, Yide Shentu, Dian Chen, Pulkit Agrawal, Trevor Darrell, Sergey Levine, Jitendra Malik
2018	—	`conf`	Zero-Shot Visual Imitation. CVPR Workshops Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Yide Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, Trevor Darrell
2018	—	`conf`	Zero-Shot Visual Imitation. ICLR Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Yide Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, Trevor Darrell
2018	J	`jnl`	Zero-Shot Visual Imitation. CoRR Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Yide Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, Trevor Darrell
2017	J	`jnl`	Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation. CoRR Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine
2017	A*	`conf`	Combining self-supervised learning and imitation for vision-based rope manipulation. ICRA Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine
2017	—	`conf`	Curiosity-Driven Exploration by Self-Supervised Prediction. CVPR Workshops Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell
2017	A*	`conf`	Curiosity-driven Exploration by Self-supervised Prediction. ICML Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell
2017	J	`jnl`	Curiosity-driven Exploration by Self-supervised Prediction. CoRR Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell
2017	J	`jnl`	Generic 3D Representation via Pose Estimation and Matching. CoRR Amir R. Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese
2017	—	`conf`	Learning to Perform Physics Experiments via Deep Reinforcement Learning. ICLR (Poster) Misha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter W. Battaglia, Nando de Freitas
2017	A*	`conf`	What will Happen Next? Forecasting Player Moves in Sports Videos. ICCV Panna Felsen, Pulkit Agrawal, Jitendra Malik
2016	—	`conf`	Generic 3D Representation via Pose Estimation and Matching. ECCV (3) Amir R. Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese
2016	A*	`conf`	Human Pose Estimation with Iterative Error Feedback. CVPR João Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik
2016	A*	`conf`	Learning Visual Predictive Models of Physics for Playing Billiards. ICLR (Poster) Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik
2016	J	`jnl`	Learning to Perform Physics Experiments via Deep Reinforcement Learning. CoRR Misha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter W. Battaglia, Nando de Freitas
2016	J	`jnl`	Learning to Poke by Poking: Experiential Learning of Intuitive Physics. CoRR Pulkit Agrawal, Ashvin Nair, Pieter Abbeel, Jitendra Malik, Sergey Levine
2016	J	`jnl`	What makes ImageNet good for transfer learning? CoRR Mi-Young Huh, Pulkit Agrawal, Alexei A. Efros
2015	J	`jnl`	Human Pose Estimation with Iterative Error Feedback. CoRR João Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik
2015	A*	`conf`	Learning to See by Moving. ICCV Pulkit Agrawal, João Carreira, Jitendra Malik
2015	J	`jnl`	Learning to See by Moving. CoRR Pulkit Agrawal, João Carreira, Jitendra Malik
2014	—	`conf`	Analyzing the Performance of Multilayer Neural Networks for Object Recognition. ECCV (7) Pulkit Agrawal, Ross B. Girshick, Jitendra Malik
2014	J	`jnl`	Analyzing the Performance of Multilayer Neural Networks for Object Recognition. CoRR Pulkit Agrawal, Ross B. Girshick, Jitendra Malik
2014	J	`jnl`	Pixels to Voxels: Modeling Visual Representation in the Human Brain. CoRR Pulkit Agrawal, Dustin Stansbury, Jitendra Malik, Jack L. Gallant
2011	—	`conf`	The automatic assessment of knowledge integration processes in project teams. CSCL Gahgene Gweon, Pulkit Agrawal, Mikesh Udani, Bhiksha Raj, Carolyn P. Rosé