Aviral Kumar

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 92

Top Topics

Partial Observability

Reinforcement Learning

Diffusion Models

Top Venues

Publications

Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data. CoRR (2024)
Katie Kang, Eric Wallace, Claire J. Tomlin, Aviral Kumar, Sergey Levine
Unfamiliar Finetuning Examples Control How Language Models Hallucinate. CoRR (2024)
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
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL. CoRR (2024)
Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar
Robotic Offline RL from Internet Videos via Value-Function Learning. ICRA (2024)
Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL. CoRR (2024)
Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar
Is Value Learning Really the Main Bottleneck in Offline RL? CoRR (2024)
Kevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Rich Walke, Chelsea Finn, Aviral Kumar, Sergey Levine
Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models. ICLR (2024)
William Chen, Oier Mees, Aviral Kumar, Sergey Levine
Vision-Language Models Provide Promptable Representations for Reinforcement Learning. CoRR (2024)
Yuxiao Qu, Tianjun Zhang, Naman Garg, Aviral Kumar
Recursive Introspection: Teaching Language Model Agents How to Self-Improve. CoRR (2024)
Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning. CoRR (2024)
Amrith Setlur, Saurabh Garg, Xinyang Geng, Naman Garg, Virginia Smith, Aviral Kumar
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold. CoRR (2024)
Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine
Efficient Deep Reinforcement Learning Requires Regulating Overfitting. CoRR (2023)
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
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions. CoRL (2023)
Mitsuhiko Nakamoto, Simon Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. NeurIPS (2023)
Joey Hong, Aviral Kumar, Sergey Levine
Confidence-Conditioned Value Functions for Offline Reinforcement Learning. ICLR (2023)
Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. NeurIPS (2023)
Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. CoRR (2023)
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
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions. CoRR (2023)
Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. CoRR (2023)
Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, Sergey Levine
ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints. NeurIPS (2023)
Han Qi, Xinyang Geng, Stefano Rando, Iku Ohama, Aviral Kumar, Sergey Levine
Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction. CoRR (2023)
Aviral Kumar, Anikait Singh, Frederik D. Ebert, Mitsuhiko Nakamoto, Yanlai Yang, Chelsea Finn, Sergey Levine
Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials. Robotics: Science and Systems (2023)
Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine
Efficient Deep Reinforcement Learning Requires Regulating Overfitting. ICLR (2023)
Jianlan Luo, Perry Dong, Jeffrey Wu, Aviral Kumar, Xinyang Geng, Sergey Levine
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning. CoRL (2023)
Kevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Walke, Chelsea Finn, Aviral Kumar, Sergey Levine
Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models. CoRR (2023)
Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar
Robotic Offline RL from Internet Videos via Value-Function Pre-Training. CoRR (2023)
Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine
Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes. ICLR (2023)
Jianlan Luo, Perry Dong, Jeffrey Wu, Aviral Kumar, Xinyang Geng, Sergey Levine
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning. CoRR (2023)
Quan Vuong, Aviral Kumar, Sergey Levine, Yevgen Chebotar
DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning. NeurIPS (2022)
Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine
Should I Run Offline Reinforcement Learning or Behavioral Cloning? ICLR (2022)
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine
How to Leverage Unlabeled Data in Offline Reinforcement Learning. CoRR (2022)
Homer Walke, Jonathan Yang, Albert Yu, Aviral Kumar, Jedrzej Orbik, Avi Singh, Sergey Levine
Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning. CoRR (2022)
Brandon Trabucco, Xinyang Geng, Aviral Kumar, Sergey Levine
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization. CoRR (2022)
Minmin Chen, Can Xu, Vince Gatto, Devanshu Jain, Aviral Kumar, Ed H. Chi
Off-Policy Actor-critic for Recommender Systems. RecSys (2022)
Brandon Trabucco, Xinyang Geng, Aviral Kumar, Sergey Levine
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization. ICML (2022)
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine
Data-Driven Offline Optimization for Architecting Hardware Accelerators. ICLR (2022)
Aviral Kumar, Anikait Singh, Frederik Ebert, Yanlai Yang, Chelsea Finn, Sergey Levine
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials. CoRR (2022)
Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning? CoRR (2022)
Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine
Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes. CoRR (2022)
Joey Hong, Aviral Kumar, Sergey Levine
Confidence-Conditioned Value Functions for Offline Reinforcement Learning. CoRR (2022)
Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. ICLR (2022)
Homer Walke, Jonathan Yang, Albert Yu, Aviral Kumar, Jedrzej Orbik, Avi Singh, Sergey Levine
Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning. CoRL (2022)
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine
How to Leverage Unlabeled Data in Offline Reinforcement Learning. ICML (2022)
Quan Vuong, Aviral Kumar, Sergey Levine, Yevgen Chebotar
Dual Generator Offline Reinforcement Learning. CoRR (2022)
Han Qi, Yi Su, Aviral Kumar, Sergey Levine
Data-Driven Offline Decision-Making via Invariant Representation Learning. NeurIPS (2022)
Han Qi, Yi Su, Aviral Kumar, Sergey Levine
Data-Driven Offline Decision-Making via Invariant Representation Learning. CoRR (2022)
Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, Sergey Levine
Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints. CoRR (2022)
Dibya Ghosh, Jad Rahme, Aviral Kumar, Amy Zhang, Ryan P. Adams, Sergey Levine
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability. NeurIPS (2021)
Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine
Conservative Objective Models for Effective Offline Model-Based Optimization. CoRR (2021)
Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine
Conservative Objective Models for Effective Offline Model-Based Optimization. ICML (2021)
Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn
COMBO: Conservative Offline Model-Based Policy Optimization. CoRR (2021)
Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn, Sergey Levine
A Workflow for Offline Model-Free Robotic Reinforcement Learning. CoRL (2021)
Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning. ICLR (2021)
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg
Conservative Safety Critics for Exploration. ICLR (2021)
Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. CoRR (2021)
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. CoRR (2021)
Dibya Ghosh, Jad Rahme, Aviral Kumar, Amy Zhang, Ryan P. Adams, Sergey Levine
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability. CoRR (2021)
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. NeurIPS (2021)
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine
Data-Driven Offline Optimization For Architecting Hardware Accelerators. CoRR (2021)
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, Thomas Paine
Benchmarks for Deep Off-Policy Evaluation. ICLR (2021)
Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn, Sergey Levine
A Workflow for Offline Model-Free Robotic Reinforcement Learning. CoRR (2021)
Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn
COMBO: Conservative Offline Model-Based Policy Optimization. NeurIPS (2021)
Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. ICLR (2021)
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
Benchmarks for Deep Off-Policy Evaluation. CoRR (2021)
Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. NeurIPS (2020)
Sergey Levine, Aviral Kumar, George Tucker, Justin Fu
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. CoRR (2020)
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg
Conservative Safety Critics for Exploration. CoRR (2020)
Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine
Conservative Q-Learning for Offline Reinforcement Learning. NeurIPS (2020)
Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine
Chaining Behaviors from Data with Model-Free Reinforcement Learning. CoRL (2020)
Aviral Kumar, Abhishek Gupta, Sergey Levine
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction. NeurIPS (2020)
Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning. CoRR (2020)
Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. CoRR (2020)
Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning. CoRR (2020)
Aviral Kumar, Sergey Levine
Model Inversion Networks for Model-Based Optimization. NeurIPS (2020)
Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine
Conservative Q-Learning for Offline Reinforcement Learning. CoRR (2020)
Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. CoRR (2020)
Aviral Kumar, Abhishek Gupta, Sergey Levine
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction. CoRR (2020)
Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine
D4RL: Datasets for Deep Data-Driven Reinforcement Learning. CoRR (2020)
Aviral Kumar, Sergey Levine
Model Inversion Networks for Model-Based Optimization. CoRR (2019)
Aviral Kumar, Sunita Sarawagi
Calibration of Encoder Decoder Models for Neural Machine Translation. CoRR (2019)
Justin Fu, Aviral Kumar, Matthew Soh, Sergey Levine
Diagnosing Bottlenecks in Deep Q-learning Algorithms. CoRR (2019)
Aviral Kumar, Justin Fu, Matthew Soh, George Tucker, Sergey Levine
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. NeurIPS (2019)
Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky
Graph Normalizing Flows. NeurIPS (2019)
Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky
Graph Normalizing Flows. CoRR (2019)
Aviral Kumar, Justin Fu, George Tucker, Sergey Levine
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. CoRR (2019)
Justin Fu, Aviral Kumar, Matthew Soh, Sergey Levine
Diagnosing Bottlenecks in Deep Q-learning Algorithms. ICML (2019)
Aviral Kumar, Xue Bin Peng, Sergey Levine
Reward-Conditioned Policies. CoRR (2019)
Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR (2019)
Aviral Kumar, Sunita Sarawagi, Ujjwal Jain
Trainable Calibration Measures For Neural Networks From Kernel Mean Embeddings. ICML (2018)
Shankara Narayanan Krishna, Aviral Kumar, Fabio Somenzi, Behrouz Touri, Ashutosh Trivedi
The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems. CoRR (2017)
Shankara Narayanan Krishna, Aviral Kumar, Fabio Somenzi, Behrouz Touri, Ashutosh Trivedi
The Reach-Avoid Problem for Constant-Rate Multi-mode Systems. ATVA (2017)
Stanley Bak, Sergiy Bogomolov, Thomas A. Henzinger, Aviral Kumar
Challenges and Tool Implementation of Hybrid Rapidly-Exploring Random Trees. NSV@CAV (2017)