Aviral Kumar - RankMe

151 papers A* 51A 1B 1Misc 6Journal 89Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames. CoRR Max Sobol Mark, Jacky Liang, Maria Attarian, Chuyuan Fu, Debidatta Dwibedi, Dhruv Shah, Aviral Kumar
2026	J	`jnl`	InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning. CoRR Matthew Y. R. Yang, Hao Bai, Ian Wu, Gene Yang, Amrith Setlur, Aviral Kumar
2026	J	`jnl`	IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL. CoRR Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang, Feng Yao, Zhengzhong Liu, Eric P. Xing, Virginia Smith, Ruslan Salakhutdinov, Zhiting Hu, Taylor W. Killian, Aviral Kumar
2026	J	`jnl`	POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration. CoRR Yuxiao Qu, Amrith Setlur, Virginia Smith, Ruslan Salakhutdinov, Aviral Kumar
2026	J	`jnl`	Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL. CoRR Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar
2026	J	`jnl`	TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks. CoRR Vansh Kapoor, Aman Gupta, Hao Chen, Anurag Beniwal, Jing Huang, Aviral Kumar
2026	J	`jnl`	WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks. CoRR Hao Bai, Alexey Taymanov, Tong Zhang, Aviral Kumar, Spencer Whitehead
2026	J	`jnl`	What Does Flow Matching Bring To TD Learning? CoRR Bhavya Agrawalla, Michal Nauman, Aviral Kumar
2025	J	`jnl`	Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners. CoRR Michal Nauman, Marek Cygan, Carmelo Sferrazza, Aviral Kumar, Pieter Abbeel
2025	J	`jnl`	CaRT: Teaching LLM Agents to Know When They Know Enough. CoRR Grace Liu, Yuxiao Qu, Jeff G. Schneider, Aarti Singh, Aviral Kumar
2025	J	`jnl`	Compute-Optimal Scaling for Value-Based Deep RL. CoRR Preston Fu, Oleh Rybkin, Zhiyuan Zhou, Michal Nauman, Pieter Abbeel, Sergey Levine, Aviral Kumar
2025	J	`jnl`	Digi-Q: Learning Q-Value Functions for Training Device-Control Agents. CoRR Hao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, Aviral Kumar
2025	A*	`conf`	Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents. ICLR Hao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, Aviral Kumar
2025	A*	`conf`	Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data. ICLR Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine, Aviral Kumar
2025	A*	`conf`	Generative Verifiers: Reward Modeling as Next-Token Prediction. ICLR Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, Rishabh Agarwal
2025	J	`jnl`	Grounded Reinforcement Learning for Visual Reasoning. CoRR Gabriel Sarch, Snigdha Saha, Naitik Khandelwal, Ayush Jain, Michael J. Tarr, Aviral Kumar, Katerina Fragkiadaki
2025	J	`jnl`	Horizon Reduction Makes RL Scalable. CoRR Seohong Park, Kevin Frans, Deepinder Mann, Benjamin Eysenbach, Aviral Kumar, Sergey Levine
2025	A*	`conf`	Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models. ICLR Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai, Aviral Kumar, Rishabh Agarwal, Sridhar Thiagarajan, Craig Boutilier, Aleksandra Faust
2025	J	`jnl`	Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning. CoRR Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar
2025	A*	`conf`	Optimizing Test-Time Compute via Meta Reinforcement Finetuning. ICML Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar
2025	J	`jnl`	RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks. CoRR Mian Wu, Gavin Zhang, Sewon Min, Sergey Levine, Aviral Kumar
2025	J	`jnl`	RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems. CoRR Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Ruslan Salakhutdinov, Chelsea Finn, Aviral Kumar
2025	A*	`conf`	RRM: Robust Reward Model Training Mitigates Reward Hacking. ICLR Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Junru Wu, Rishabh Joshi, Yang Gao, Jiaming Shen, Zhen Qin, Tianhe Yu, Daniel Sohn, Anastasia Makarova, Jeremiah Zhe Liu, Yuan Liu, Bilal Piot, Abe Ittycheriah, Aviral Kumar, Mohammad Saleh
2025	J	`jnl`	RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction. CoRR Zheyuan Hu, Robyn Wu, Naveen Enock, Jasmine Li, Riya Kadakia, Zackory Erickson, Aviral Kumar
2025	J	`jnl`	Reasoning as an Adaptive Defense for Safety. CoRR Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan, Aviral Kumar
2025	A*	`conf`	Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning. ICLR Amrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, Aviral Kumar
2025	A*	`conf`	Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning. ICLR Charlie Victor Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
2025	A*	`conf`	Scaling Test-Time Compute Without Verification or RL is Suboptimal. ICML Amrith Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar
2025	J	`jnl`	Scaling Test-Time Compute Without Verification or RL is Suboptimal. CoRR Amrith Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar
2025	J	`jnl`	Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction. CoRR Junhong Shen, Hao Bai, Lunjun Zhang, Yifei Zhou, Amrith Setlur, Shengbang Tong, Diego Caples, Nan Jiang, Tong Zhang, Ameet Talwalkar, Aviral Kumar
2025	A*	`conf`	Training Language Models to Self-Correct via Reinforcement Learning. ICLR Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D. Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M. Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal M. P. Behbahani, Aleksandra Faust
2025	—	`conf`	Unfamiliar Finetuning Examples Control How Language Models Hallucinate. NAACL (Long Papers) Katie Kang, Eric Wallace, Claire J. Tomlin, Aviral Kumar, Sergey Levine
2025	A*	`conf`	Value-Based Deep RL Scales Predictably. ICML Oleh Rybkin, Michal Nauman, Preston Fu, Charlie Victor Snell, Pieter Abbeel, Sergey Levine, Aviral Kumar
2025	J	`jnl`	Value-Based Deep RL Scales Predictably. CoRR Oleh Rybkin, Michal Nauman, Preston Fu, Charlie Snell, Pieter Abbeel, Sergey Levine, Aviral Kumar
2025	J	`jnl`	Vision-Language Models Provide Promptable Representations for Reinforcement Learning. Trans. Mach. Learn. Res. William Chen, Oier Mees, Aviral Kumar, Sergey Levine
2025	A*	`conf`	What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? ICML Katie Kang, Amrith Setlur, Dibya Ghosh, Jacob Steinhardt, Claire J. Tomlin, Sergey Levine, Aviral Kumar
2025	J	`jnl`	e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs. CoRR Amrith Setlur, Matthew Y. R. Yang, Charlie Snell, Jeremy Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar
2025	J	`jnl`	floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL. CoRR Bhavya Agrawalla, Michal Nauman, Khush Agarwal, Aviral Kumar
2024	A*	`conf`	ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL. ICML Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
2024	J	`jnl`	ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL. CoRR Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
2024	J	`jnl`	D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning. RLJ Rafael Rafailov, Kyle Beltran Hatch, Anikait Singh, Aviral Kumar, Laura Smith, Ilya Kostrikov, Philippe Hansen-Estruch, Victor Kolev, Philip J. Ball, Jiajun Wu, Sergey Levine, Chelsea Finn
2024	J	`jnl`	D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning. CoRR Rafael Rafailov, Kyle Hatch, Anikait Singh, Laura Smith, Aviral Kumar, Ilya Kostrikov, Philippe Hansen-Estruch, Victor Kolev, Philip J. Ball, Jiajun Wu, Chelsea Finn, Sergey Levine
2024	A*	`conf`	Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization. NeurIPS Aniketh Janardhan Reddy, Xinyang Geng, Michael Herschl, Sathvik Kolli, Aviral Kumar, Patrick Hsu, Sergey Levine, Nilah Ioannidis
2024	A*	`conf`	DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning. NeurIPS Hao Bai, Yifei Zhou, Jiayi Pan, Mert Cemri, Alane Suhr, Sergey Levine, Aviral Kumar
2024	J	`jnl`	DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning. CoRR Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
2024	J	`jnl`	Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data. CoRR Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine, Aviral Kumar
2024	J	`jnl`	Generative Verifiers: Reward Modeling as Next-Token Prediction. CoRR Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, Rishabh Agarwal
2024	J	`jnl`	Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models. CoRR Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai, Sridhar Thiagarajan, Craig Boutilier, Rishabh Agarwal, Aviral Kumar, Aleksandra Faust
2024	A*	`conf`	Is Value Learning Really the Main Bottleneck in Offline RL? NeurIPS Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar
2024	J	`jnl`	Is Value Learning Really the Main Bottleneck in Offline RL? CoRR Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar
2024	J	`jnl`	Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone. CoRR Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, Mohan Kumar Srirama, Archit Sharma, Chelsea Finn, Aviral Kumar
2024	A*	`conf`	Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data. ICML Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar
2024	J	`jnl`	Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data. CoRR Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar
2024	A*	`conf`	RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold. NeurIPS Amrith Setlur, Saurabh Garg, Xinyang Geng, Naman Garg, Virginia Smith, Aviral Kumar
2024	J	`jnl`	RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold. CoRR Amrith Setlur, Saurabh Garg, Xinyang Geng, Naman Garg, Virginia Smith, Aviral Kumar
2024	J	`jnl`	RRM: Robust Reward Model Training Mitigates Reward Hacking. CoRR Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Junru Wu, Rishabh Joshi, Yang Gao, Jiaming Shen, Zhen Qin, Tianhe Yu, Daniel Sohn, Anastasiia Makarova, Jeremiah Z. Liu, Yuan Liu, Bilal Piot, Abe Ittycheriah, Aviral Kumar, Mohammad Saleh
2024	A*	`conf`	Recursive Introspection: Teaching Language Model Agents How to Self-Improve. NeurIPS Yuxiao Qu, Tianjun Zhang, Naman Garg, Aviral Kumar
2024	J	`jnl`	Recursive Introspection: Teaching Language Model Agents How to Self-Improve. CoRR Yuxiao Qu, Tianjun Zhang, Naman Garg, Aviral Kumar
2024	J	`jnl`	Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning. CoRR Amrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, Aviral Kumar
2024	A*	`conf`	Robotic Offline RL from Internet Videos via Value-Function Learning. ICRA Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar
2024	J	`jnl`	Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters. CoRR Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
2024	Misc	`conf`	Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance. CoRL Mitsuhiko Nakamoto, Oier Mees, Aviral Kumar, Sergey Levine
2024	J	`jnl`	Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance. CoRR Mitsuhiko Nakamoto, Oier Mees, Aviral Kumar, Sergey Levine
2024	A*	`conf`	Stop Regressing: Training Value Functions via Classification for Scalable Deep RL. ICML Jesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taïga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, Rishabh Agarwal
2024	J	`jnl`	Stop Regressing: Training Value Functions via Classification for Scalable Deep RL. CoRR Jesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taïga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, Rishabh Agarwal
2024	J	`jnl`	Training Language Models to Self-Correct via Reinforcement Learning. CoRR Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D. Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M. Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal M. P. Behbahani, Aleksandra Faust
2024	J	`jnl`	Unfamiliar Finetuning Examples Control How Language Models Hallucinate. CoRR Katie Kang, Eric Wallace, Claire J. Tomlin, Aviral Kumar, Sergey Levine
2024	J	`jnl`	Vision-Language Models Provide Promptable Representations for Reinforcement Learning. CoRR William Chen, Oier Mees, Aviral Kumar, Sergey Levine
2024	J	`jnl`	What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? CoRR Katie Kang, Amrith Setlur, Dibya Ghosh, Jacob Steinhardt, Claire J. Tomlin, Sergey Levine, Aviral Kumar
2024	A*	`conf`	Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models. ICLR Kevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Rich Walke, Chelsea Finn, Aviral Kumar, Sergey Levine
2023	Misc	`conf`	Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning. CoRL Jianlan Luo, Perry Dong, Jeffrey Wu, Aviral Kumar, Xinyang Geng, Sergey Levine
2023	J	`jnl`	Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning. CoRR Jianlan Luo, Perry Dong, Jeffrey Wu, Aviral Kumar, Xinyang Geng, Sergey Levine
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	A*	`conf`	Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. NeurIPS Mitsuhiko Nakamoto, Simon Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
2023	J	`jnl`	Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. CoRR Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
2023	A*	`conf`	Confidence-Conditioned Value Functions for Offline Reinforcement Learning. ICLR Joey Hong, Aviral Kumar, Sergey Levine
2023	A*	`conf`	Efficient Deep Reinforcement Learning Requires Regulating Overfitting. ICLR Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine
2023	J	`jnl`	Efficient Deep Reinforcement Learning Requires Regulating Overfitting. CoRR Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine
2023	J	`jnl`	Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction. CoRR Han Qi, Xinyang Geng, Stefano Rando, Iku Ohama, Aviral Kumar, Sergey Levine
2023	A*	`conf`	Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes. ICLR Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine
2023	—	`conf`	Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials. Robotics: Science and Systems Aviral Kumar, Anikait Singh, Frederik D. Ebert, Mitsuhiko Nakamoto, Yanlai Yang, Chelsea Finn, Sergey Levine
2023	Misc	`conf`	Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions. CoRL Yevgen Chebotar, Quan Vuong, Karol Hausman, Fei Xia, Yao Lu, Alex Irpan, Aviral Kumar, Tianhe Yu, Alexander Herzog, Karl Pertsch, Keerthana Gopalakrishnan, Julian Ibarz, Ofir Nachum, Sumedh Anand Sontakke, Grecia Salazar, Huong T. Tran, Jodilyn Peralta, Clayton Tan, Deeksha Manjunath, Jaspiar Singh, Brianna Zitkovich, Tomas Jackson, Kanishka Rao, Chelsea Finn, Sergey Levine
2023	J	`jnl`	Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions. CoRR Yevgen Chebotar, Quan Vuong, Alex Irpan, Karol Hausman, Fei Xia, Yao Lu, Aviral Kumar, Tianhe Yu, Alexander Herzog, Karl Pertsch, Keerthana Gopalakrishnan, Julian Ibarz, Ofir Nachum, Sumedh Sontakke, Grecia Salazar, Huong T. Tran, Jodilyn Peralta, Clayton Tan, Deeksha Manjunath, Jaspiar Singh, Brianna Zitkovich, Tomas Jackson, Kanishka Rao, Chelsea Finn, Sergey Levine
2023	A*	`conf`	ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints. NeurIPS Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, Sergey Levine
2023	J	`jnl`	Robotic Offline RL from Internet Videos via Value-Function Pre-Training. CoRR Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar
2023	J	`jnl`	Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models. CoRR Kevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Walke, Chelsea Finn, Aviral Kumar, Sergey Levine
2022	J	`jnl`	Confidence-Conditioned Value Functions for Offline Reinforcement Learning. CoRR Joey Hong, Aviral Kumar, Sergey Levine
2022	A*	`conf`	DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning. NeurIPS Quan Vuong, Aviral Kumar, Sergey Levine, Yevgen Chebotar
2022	A*	`conf`	DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. ICLR Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
2022	A*	`conf`	Data-Driven Offline Decision-Making via Invariant Representation Learning. NeurIPS Han Qi, Yi Su, Aviral Kumar, Sergey Levine
2022	J	`jnl`	Data-Driven Offline Decision-Making via Invariant Representation Learning. CoRR Han Qi, Yi Su, Aviral Kumar, Sergey Levine
2022	A*	`conf`	Data-Driven Offline Optimization for Architecting Hardware Accelerators. ICLR Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine
2022	A*	`conf`	Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization. ICML Brandon Trabucco, Xinyang Geng, Aviral Kumar, Sergey Levine
2022	J	`jnl`	Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization. CoRR Brandon Trabucco, Xinyang Geng, Aviral Kumar, Sergey Levine
2022	Misc	`conf`	Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning. CoRL Homer Walke, Jonathan Yang, Albert Yu, Aviral Kumar, Jedrzej Orbik, Avi Singh, Sergey Levine
2022	J	`jnl`	Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning. CoRR Homer Walke, Jonathan Yang, Albert Yu, Aviral Kumar, Jedrzej Orbik, Avi Singh, Sergey Levine
2022	J	`jnl`	Dual Generator Offline Reinforcement Learning. CoRR Quan Vuong, Aviral Kumar, Sergey Levine, Yevgen Chebotar
2022	A*	`conf`	How to Leverage Unlabeled Data in Offline Reinforcement Learning. ICML Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine
2022	J	`jnl`	How to Leverage Unlabeled Data in Offline Reinforcement Learning. CoRR Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine
2022	A	`conf`	Off-Policy Actor-critic for Recommender Systems. RecSys Minmin Chen, Can Xu, Vince Gatto, Devanshu Jain, Aviral Kumar, Ed H. Chi
2022	J	`jnl`	Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes. CoRR Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine
2022	J	`jnl`	Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints. CoRR Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, Sergey Levine
2022	J	`jnl`	Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials. CoRR Aviral Kumar, Anikait Singh, Frederik Ebert, Yanlai Yang, Chelsea Finn, Sergey Levine
2022	A*	`conf`	Should I Run Offline Reinforcement Learning or Behavioral Cloning? ICLR Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine
2022	J	`jnl`	When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning? CoRR Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine
2021	Misc	`conf`	A Workflow for Offline Model-Free Robotic Reinforcement Learning. CoRL Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn, Sergey Levine
2021	J	`jnl`	A Workflow for Offline Model-Free Robotic Reinforcement Learning. CoRR Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn, Sergey Levine
2021	A*	`conf`	Benchmarks for Deep Off-Policy Evaluation. ICLR Justin Fu, Mohammad Norouzi, Ofir Nachum, George Tucker, Ziyu Wang, Alexander Novikov, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Tom Le Paine
2021	J	`jnl`	Benchmarks for Deep Off-Policy Evaluation. CoRR Justin Fu, Mohammad Norouzi, Ofir Nachum, George Tucker, Ziyu Wang, Alexander Novikov, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Tom Le Paine
2021	A*	`conf`	COMBO: Conservative Offline Model-Based Policy Optimization. NeurIPS Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn
2021	J	`jnl`	COMBO: Conservative Offline Model-Based Policy Optimization. CoRR Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn
2021	A*	`conf`	Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. NeurIPS Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn
2021	J	`jnl`	Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. CoRR Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn
2021	A*	`conf`	Conservative Objective Models for Effective Offline Model-Based Optimization. ICML Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine
2021	J	`jnl`	Conservative Objective Models for Effective Offline Model-Based Optimization. CoRR Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine
2021	A*	`conf`	Conservative Safety Critics for Exploration. ICLR Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg
2021	J	`jnl`	DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. CoRR Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
2021	J	`jnl`	Data-Driven Offline Optimization For Architecting Hardware Accelerators. CoRR Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine
2021	A*	`conf`	Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning. ICLR Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
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`	Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability. NeurIPS Dibya Ghosh, Jad Rahme, Aviral Kumar, Amy Zhang, Ryan P. Adams, Sergey Levine
2021	J	`jnl`	Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability. CoRR Dibya Ghosh, Jad Rahme, Aviral Kumar, Amy Zhang, Ryan P. Adams, Sergey Levine
2020	J	`jnl`	COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning. CoRR Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine
2020	Misc	`conf`	Chaining Behaviors from Data with Model-Free Reinforcement Learning. CoRL Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine
2020	A*	`conf`	Conservative Q-Learning for Offline Reinforcement Learning. NeurIPS Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine
2020	J	`jnl`	Conservative Q-Learning for Offline Reinforcement Learning. CoRR Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine
2020	J	`jnl`	Conservative Safety Critics for Exploration. CoRR Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg
2020	J	`jnl`	D4RL: Datasets for Deep Data-Driven Reinforcement Learning. CoRR Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine
2020	A*	`conf`	DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction. NeurIPS Aviral Kumar, Abhishek Gupta, Sergey Levine
2020	J	`jnl`	DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction. CoRR Aviral Kumar, Abhishek Gupta, Sergey Levine
2020	J	`jnl`	Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning. CoRR Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
2020	A*	`conf`	Model Inversion Networks for Model-Based Optimization. NeurIPS Aviral Kumar, Sergey Levine
2020	J	`jnl`	OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. CoRR Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum
2020	J	`jnl`	Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. CoRR Sergey Levine, Aviral Kumar, George Tucker, Justin Fu
2020	A*	`conf`	One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. NeurIPS Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn
2020	J	`jnl`	One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. CoRR Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn
2019	J	`jnl`	Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine
2019	J	`jnl`	Calibration of Encoder Decoder Models for Neural Machine Translation. CoRR Aviral Kumar, Sunita Sarawagi
2019	A*	`conf`	Diagnosing Bottlenecks in Deep Q-learning Algorithms. ICML Justin Fu, Aviral Kumar, Matthew Soh, Sergey Levine
2019	J	`jnl`	Diagnosing Bottlenecks in Deep Q-learning Algorithms. CoRR Justin Fu, Aviral Kumar, Matthew Soh, Sergey Levine
2019	A*	`conf`	Graph Normalizing Flows. NeurIPS Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky
2019	J	`jnl`	Graph Normalizing Flows. CoRR Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky
2019	J	`jnl`	Model Inversion Networks for Model-Based Optimization. CoRR Aviral Kumar, Sergey Levine
2019	J	`jnl`	Reward-Conditioned Policies. CoRR Aviral Kumar, Xue Bin Peng, Sergey Levine
2019	A*	`conf`	Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. NeurIPS Aviral Kumar, Justin Fu, Matthew Soh, George Tucker, Sergey Levine
2019	J	`jnl`	Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. CoRR Aviral Kumar, Justin Fu, George Tucker, Sergey Levine
2018	A*	`conf`	Trainable Calibration Measures For Neural Networks From Kernel Mean Embeddings. ICML Aviral Kumar, Sunita Sarawagi, Ujjwal Jain
2017	—	`conf`	Challenges and Tool Implementation of Hybrid Rapidly-Exploring Random Trees. NSV@CAV Stanley Bak, Sergiy Bogomolov, Thomas A. Henzinger, Aviral Kumar
2017	J	`jnl`	The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems. CoRR Shankara Narayanan Krishna, Aviral Kumar, Fabio Somenzi, Behrouz Touri, Ashutosh Trivedi
2017	B	`conf`	The Reach-Avoid Problem for Constant-Rate Multi-mode Systems. ATVA Shankara Narayanan Krishna, Aviral Kumar, Fabio Somenzi, Behrouz Touri, Ashutosh Trivedi