William F. Whitney

机构：DeepMind · 主页：http://willwhitney.com

发表论文 28 篇 · 总被引 1629 次 · h-index 14

代表论文

• Offline RL Without Off-Policy Evaluation (2021 · Neural Information Processing Systems · 被引 209)
• Learning rigid dynamics with face interaction graph networks (2022 · International Conference on Learning Representations · 被引 59)
• Dynamics-aware Embeddings (2019 · International Conference on Learning Representations · 被引 59)
• Model-Based Planning with Discrete and Continuous Actions (2017 · 被引 55)
• Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning (2017 · 被引 43)
• The Challenges of Exploration for Offline Reinforcement Learning (2022 · arXiv.org · 被引 33)