3.7k citations · 6.5k across the 10 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 4 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.LG2021★ 6 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…