Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Aviral Kumar

Aviral Kumar

A Workflow for Offline Model-Free Robotic Reinforcement Learning


Sep 23, 2021
Aviral Kumar, Anikait Singh, Stephen Tian, Chelsea Finn, Sergey Levine

Figure 1 for A Workflow for Offline Model-Free Robotic Reinforcement Learning
Figure 2 for A Workflow for Offline Model-Free Robotic Reinforcement Learning
Figure 3 for A Workflow for Offline Model-Free Robotic Reinforcement Learning
Figure 4 for A Workflow for Offline Model-Free Robotic Reinforcement Learning
* CoRL 2021. Project Website: https://sites.google.com/view/offline-rl-workflow. First two authors contributed equally 
  Access Paper or Ask Questions

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning


Sep 16, 2021
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn

Figure 1 for Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Figure 2 for Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Figure 3 for Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Figure 4 for Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

  Access Paper or Ask Questions

Conservative Objective Models for Effective Offline Model-Based Optimization


Jul 14, 2021
Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine

Figure 1 for Conservative Objective Models for Effective Offline Model-Based Optimization
Figure 2 for Conservative Objective Models for Effective Offline Model-Based Optimization
Figure 3 for Conservative Objective Models for Effective Offline Model-Based Optimization
Figure 4 for Conservative Objective Models for Effective Offline Model-Based Optimization
* ICML 2021. First two authors contributed equally. Code at: https://github.com/brandontrabucco/design-baselines/blob/c65a53fe1e6567b740f0adf60c5db9921c1f2330/design_baselines/coms_cleaned/__init__.py 
  Access Paper or Ask Questions

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability


Jul 13, 2021
Dibya Ghosh, Jad Rahme, Aviral Kumar, Amy Zhang, Ryan P. Adams, Sergey Levine

Figure 1 for Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Figure 2 for Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Figure 3 for Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Figure 4 for Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
* First two authors contributed equally 
  Access Paper or Ask Questions

Benchmarks for Deep Off-Policy Evaluation


Mar 30, 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

Figure 1 for Benchmarks for Deep Off-Policy Evaluation
Figure 2 for Benchmarks for Deep Off-Policy Evaluation
Figure 3 for Benchmarks for Deep Off-Policy Evaluation
Figure 4 for Benchmarks for Deep Off-Policy Evaluation
* ICLR 2021 paper. Policies and evaluation code are available at https://github.com/google-research/deep_ope 
  Access Paper or Ask Questions

COMBO: Conservative Offline Model-Based Policy Optimization


Feb 16, 2021
Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn

Figure 1 for COMBO: Conservative Offline Model-Based Policy Optimization
Figure 2 for COMBO: Conservative Offline Model-Based Policy Optimization
Figure 3 for COMBO: Conservative Offline Model-Based Policy Optimization
Figure 4 for COMBO: Conservative Offline Model-Based Policy Optimization

  Access Paper or Ask Questions

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning


Oct 27, 2020
Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine

Figure 1 for COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
Figure 2 for COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
Figure 3 for COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
Figure 4 for COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
* Accepted to CoRL 2020. Source code and videos available at https://sites.google.com/view/cog-rl 
  Access Paper or Ask Questions

Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning


Oct 27, 2020
Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine

Figure 1 for Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Figure 2 for Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Figure 3 for Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Figure 4 for Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
* Pre-print. First two authors contributed equally 
  Access Paper or Ask Questions

Conservative Safety Critics for Exploration


Oct 27, 2020
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg

Figure 1 for Conservative Safety Critics for Exploration
Figure 2 for Conservative Safety Critics for Exploration
Figure 3 for Conservative Safety Critics for Exploration
Figure 4 for Conservative Safety Critics for Exploration
* Preprint. Under review 
  Access Paper or Ask Questions

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL


Oct 27, 2020
Saurabh Kumar, Aviral Kumar, Sergey Levine, Chelsea Finn

Figure 1 for One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
Figure 2 for One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
Figure 3 for One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
* Accepted at NeurIPS 2020 
  Access Paper or Ask Questions

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning


Oct 27, 2020
Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum

Figure 1 for OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
Figure 2 for OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
Figure 3 for OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
Figure 4 for OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
* https://sites.google.com/view/opal-iclr 
  Access Paper or Ask Questions

Conservative Q-Learning for Offline Reinforcement Learning


Jun 29, 2020
Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine

Figure 1 for Conservative Q-Learning for Offline Reinforcement Learning
Figure 2 for Conservative Q-Learning for Offline Reinforcement Learning
Figure 3 for Conservative Q-Learning for Offline Reinforcement Learning
Figure 4 for Conservative Q-Learning for Offline Reinforcement Learning
* Preprint. Website at: https://sites.google.com/view/cql-offline-rl 
  Access Paper or Ask Questions

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems


May 04, 2020
Sergey Levine, Aviral Kumar, George Tucker, Justin Fu

Figure 1 for Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Figure 2 for Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Figure 3 for Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Figure 4 for Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

  Access Paper or Ask Questions

D4RL: Datasets for Deep Data-Driven Reinforcement Learning


Apr 20, 2020
Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine

Figure 1 for D4RL: Datasets for Deep Data-Driven Reinforcement Learning
Figure 2 for D4RL: Datasets for Deep Data-Driven Reinforcement Learning
Figure 3 for D4RL: Datasets for Deep Data-Driven Reinforcement Learning
* Website available at https://sites.google.com/view/d4rl/home 
  Access Paper or Ask Questions

Datasets for Data-Driven Reinforcement Learning


Apr 15, 2020
Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine

Figure 1 for Datasets for Data-Driven Reinforcement Learning
Figure 2 for Datasets for Data-Driven Reinforcement Learning
Figure 3 for Datasets for Data-Driven Reinforcement Learning

  Access Paper or Ask Questions

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction


Mar 16, 2020
Aviral Kumar, Abhishek Gupta, Sergey Levine

Figure 1 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 2 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 3 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 4 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
* Pre-print 
  Access Paper or Ask Questions

Reward-Conditioned Policies


Dec 31, 2019
Aviral Kumar, Xue Bin Peng, Sergey Levine

Figure 1 for Reward-Conditioned Policies
Figure 2 for Reward-Conditioned Policies
Figure 3 for Reward-Conditioned Policies
Figure 4 for Reward-Conditioned Policies

  Access Paper or Ask Questions

Model Inversion Networks for Model-Based Optimization


Dec 31, 2019
Aviral Kumar, Sergey Levine

Figure 1 for Model Inversion Networks for Model-Based Optimization
Figure 2 for Model Inversion Networks for Model-Based Optimization
Figure 3 for Model Inversion Networks for Model-Based Optimization
Figure 4 for Model Inversion Networks for Model-Based Optimization

  Access Paper or Ask Questions

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning


Oct 07, 2019
Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine

Figure 1 for Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Figure 2 for Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Figure 3 for Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Figure 4 for Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

  Access Paper or Ask Questions

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction


Jun 03, 2019
Aviral Kumar, Justin Fu, George Tucker, Sergey Levine

Figure 1 for Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
Figure 2 for Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
Figure 3 for Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
Figure 4 for Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction

  Access Paper or Ask Questions

Graph Normalizing Flows


May 30, 2019
Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky

Figure 1 for Graph Normalizing Flows
Figure 2 for Graph Normalizing Flows
Figure 3 for Graph Normalizing Flows
Figure 4 for Graph Normalizing Flows

  Access Paper or Ask Questions

Calibration of Encoder Decoder Models for Neural Machine Translation


Mar 03, 2019
Aviral Kumar, Sunita Sarawagi

Figure 1 for Calibration of Encoder Decoder Models for Neural Machine Translation
Figure 2 for Calibration of Encoder Decoder Models for Neural Machine Translation
Figure 3 for Calibration of Encoder Decoder Models for Neural Machine Translation
Figure 4 for Calibration of Encoder Decoder Models for Neural Machine Translation
* 12 Pages 
  Access Paper or Ask Questions

Diagnosing Bottlenecks in Deep Q-learning Algorithms


Feb 26, 2019
Justin Fu, Aviral Kumar, Matthew Soh, Sergey Levine

Figure 1 for Diagnosing Bottlenecks in Deep Q-learning Algorithms
Figure 2 for Diagnosing Bottlenecks in Deep Q-learning Algorithms
Figure 3 for Diagnosing Bottlenecks in Deep Q-learning Algorithms
Figure 4 for Diagnosing Bottlenecks in Deep Q-learning Algorithms

  Access Paper or Ask Questions

The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems


Jul 12, 2017
Shankara Narayanan Krishna, Aviral Kumar, Fabio Somenzi, Behrouz Touri, Ashutosh Trivedi

Figure 1 for The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems
Figure 2 for The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems
Figure 3 for The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems
Figure 4 for The Reach-Avoid Problem for Constant-Rate Multi-Mode Systems
* 26 pages 
  Access Paper or Ask Questions