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
Posted Content
Hierarchical visuomotor control of humanoids
Josh Merel,Arun Ahuja,Vu Pham,Saran Tunyasuvunakool,Siqi Liu,Dhruva Tirumala,Nicolas Heess,Greg Wayne +7 more
TL;DR: In this article, a task-directed motor controller was developed for a humanoid agent to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment.
Proceedings Article
Scaling memory-augmented neural networks with sparse reads and writes
Jack W. Rae,Jonathan J. Hunt,Tim Harley,Ivo Danihelka,Andrew W. Senior,Greg Wayne,Alex Graves,Timothy P. Lillicrap +7 more
TL;DR: This work presents an end-to-end differentiable memory access scheme, which they call Sparse Access Memory (SAM), that retains the representational power of the original approaches whilst training efficiently with very large memories, and achieves asymptotic lower bounds in space and time complexity.
Posted Content
Generative Temporal Models with Memory
Mevlana Gemici,Chia-Chun Hung,Adam Santoro,Greg Wayne,Shakir Mohamed,Danilo Jimenez Rezende,David Amos,Timothy P. Lillicrap +7 more
TL;DR: Generative Temporal Models augmented with external memory systems are introduced and it is shown that these models store information from early in a sequence, and reuse this stored information efficiently, which allows them to perform substantially better than existing models based on well-known recurrent neural networks, like LSTMs.
Proceedings Article
Hierarchical Visuomotor Control of Humanoids.
Josh Merel,Arun Ahuja,Vu Pham,Saran Tunyasuvunakool,Siqi Liu,Dhruva Tirumala,Nicolas Heess,Greg Wayne +7 more
TL;DR: In this article, a task-directed motor controller was developed for a humanoid agent to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment.
Posted Content
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
Dhruva Tirumala,Hyeonwoo Noh,Alexandre Galashov,Leonard Hasenclever,Arun Ahuja,Greg Wayne,Razvan Pascanu,Yee Whye Teh,Nicolas Heess +8 more
TL;DR: This work considers the implications of the KL-regularized expected reward objective framework in cases where both the policy and default behavior are augmented with latent variables and discusses how the resulting hierarchical structures can be used to implement different inductive biases and how their modularity can benefit transfer.