Alert button
Picture for Aviral Kumar

Aviral Kumar

Alert button

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Oct 12, 2023
Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal

Viaarxiv icon

Robotic Offline RL from Internet Videos via Value-Function Pre-Training

Sep 22, 2023
Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar

Figure 1 for Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Figure 2 for Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Figure 3 for Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Figure 4 for Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Viaarxiv icon

Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

Sep 18, 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 Singht, Brianna Zitkovich, Tomas Jackson, Kanishka Rao, Chelsea Finn, Sergey Levine

Figure 1 for Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Figure 2 for Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Figure 3 for Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Figure 4 for Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Viaarxiv icon

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

Apr 20, 2023
Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine

Figure 1 for Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Figure 2 for Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Figure 3 for Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Figure 4 for Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Viaarxiv icon

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Mar 09, 2023
Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine

Figure 1 for Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Figure 2 for Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Figure 3 for Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Figure 4 for Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Viaarxiv icon

Confidence-Conditioned Value Functions for Offline Reinforcement Learning

Dec 08, 2022
Joey Hong, Aviral Kumar, Sergey Levine

Figure 1 for Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Figure 2 for Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Figure 3 for Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Figure 4 for Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Viaarxiv icon

Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes

Nov 28, 2022
Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine

Figure 1 for Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
Figure 2 for Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
Figure 3 for Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
Figure 4 for Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
Viaarxiv icon

Data-Driven Offline Decision-Making via Invariant Representation Learning

Nov 25, 2022
Han Qi, Yi Su, Aviral Kumar, Sergey Levine

Figure 1 for Data-Driven Offline Decision-Making via Invariant Representation Learning
Figure 2 for Data-Driven Offline Decision-Making via Invariant Representation Learning
Figure 3 for Data-Driven Offline Decision-Making via Invariant Representation Learning
Figure 4 for Data-Driven Offline Decision-Making via Invariant Representation Learning
Viaarxiv icon