G
Greg Wayne
Researcher at Google
Publications - 45
Citations - 8657
Greg Wayne is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 26, co-authored 45 publications receiving 7065 citations.
Papers
More filters
Proceedings Article
Robust imitation of diverse behaviors
TL;DR: A new version of GAIL is developed that is much more robust than the purely-supervised controller, especially with few demonstrations, and avoids mode collapse, capturing many diverse behaviors when GAIL on its own does not.
Posted ContentDOI
Towards an integration of deep learning and neuroscience
TL;DR: The authors hypothesize that the brain optimizes cost functions, these cost functions are diverse and differ across brain locations and over development, and optimization operates within a pre-structured architecture matched to the computational problems posed by behavior.
Journal ArticleDOI
Optimizing agent behavior over long time scales by transporting value.
Chia-Chun Hung,Timothy P. Lillicrap,Josh Abramson,Yan Wu,Mehdi Mirza,Federico Carnevale,Arun Ahuja,Greg Wayne +7 more
TL;DR: Here, the authors show how a mechanism that connects learning from delayed rewards with memory retrieval can enable AI agents to discover links between past events to help decide better courses of action in the future.
Posted Content
Neural probabilistic motor primitives for humanoid control
Josh Merel,Leonard Hasenclever,Alexandre Galashov,Arun Ahuja,Vu Pham,Greg Wayne,Yee Whye Teh,Nicolas Heess +7 more
TL;DR: A motor architecture that has the general structure of an inverse model with a latent-variable bottleneck is proposed, and it is shown that it is possible to train this model entirely offline to compress thousands of expert policies and learn a motor primitive embedding space.
Proceedings Article
Neural Probabilistic Motor Primitives for Humanoid Control
Josh Merel,Leonard Hasenclever,Alexandre Galashov,Arun Ahuja,Vu Pham,Greg Wayne,Yee Whye Teh,Nicolas Heess +7 more
TL;DR: In this paper, the authors propose a motor architecture that has the general structure of an inverse model with a latent-variable bottleneck, and show that it is possible to train this model entirely offline to compress thousands of expert policies.