← Authors

Aurick Zhou

8 papers · 2018–2023 · 4 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (17) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (5) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (6) 🌈 Renaissance Researcher (5) πŸ“ˆ Trend Setter

Conferences

ICML (4) NIPS (2) ICCV (1) RSS (1)

Top co-authors

Sergey Levine (7) George Tucker (2) Tuomas Haarnoja (2) Deirdre Quillen (1) Abhishek Gupta (1) Sehoon Ha (1) Pieter Abbeel (1) Ari Seff (1) Rami Al-Rfou (1) Ashwin Reddy (1)

Research topics

Reinforcement Learning (1) Robotics (1)

Keywords

maximum entropy (2) uncertainty estimation (2) off-policy learning (2) deep reinforcement learning (2) domain adaptation (1) entropy minimization (1) sample efficiency (1) out-of-distribution detection (1) language modeling (1) trajectory prediction (1) motion forecasting (1) posterior sampling (1) covariate shift (1) continuous control (1) reward learning (1) uncertainty quantification (1) distribution shift (1) normalized maximum likelihood (1) bayesian inference (1) offline reinforcement learning (1)

Papers

MotionLM: Multi-Agent Motion Forecasting as Language Modeling ICCV 2023
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning ICML 2021
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation ICML 2021
Bayesian Adaptation for Covariate Shift NIPS 2021
Conservative Q-Learning for Offline Reinforcement Learning NIPS 2020
Learning to Walk Via Deep Reinforcement Learning RSS 2019
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables ICML 2019
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor ICML 2018