activity
20182021
most citedConservative Q-Learning for Offline Reinforcement Learning

538 citations · 781 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG20214 cited

Training on Test Data with Bayesian Adaptation for Covariate Shift

Aurick Zhou, Sergey Levine

When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neu…

cs.LG20216 cited

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

Kevin Li, Abhishek Gupta, Ashwin Reddy +4

Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Ca…

cs.LG20205 cited

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation

Aurick Zhou, Sergey Levine

While deep neural networks provide good performance for a range of challenging tasks, calibration and uncertainty estimation remain major challenges, especially under distribution…

cs.LG2020538 cited

Conservative Q-Learning for Offline Reinforcement Learning

Aviral Kumar, Aurick Zhou, George Tucker +1

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise…

cs.LG2019228 cited

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

Kate Rakelly, Aurick Zhou, Deirdre Quillen +2

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable a…

cs.LG2019

Soft Actor-Critic Algorithms and Applications

Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen +8

Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods…