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

Add to Chrome

Add to Firefox

Picture for Aviral Kumar

Aviral Kumar

When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Apr 12, 2022
Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine

Figure 1 for When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Figure 2 for When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Figure 3 for When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Figure 4 for When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

* ICLR 2022. First two authors contributed equally

Access Paper or Ask Questions

Data-Driven Offline Optimization For Architecting Hardware Accelerators

Oct 20, 2021
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Figure 1 for Data-Driven Offline Optimization For Architecting Hardware Accelerators

Figure 2 for Data-Driven Offline Optimization For Architecting Hardware Accelerators

Figure 3 for Data-Driven Offline Optimization For Architecting Hardware Accelerators

Figure 4 for Data-Driven Offline Optimization For Architecting Hardware Accelerators

* First two authors contributed equally

Access Paper or Ask Questions

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 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