J
Jonathan Schwarz
Researcher at Google
Publications - 21
Citations - 2532
Jonathan Schwarz 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 15, co-authored 21 publications receiving 1507 citations.
Papers
More filters
Proceedings Article
Progress & Compress: A scalable framework for continual learning
Journal ArticleDOI
The NarrativeQA Reading Comprehension Challenge
Tomáš Kočiský,Jonathan Schwarz,Phil Blunsom,Chris Dyer,Karl Moritz Hermann,Gábor Melis,Edward Grefenstette +6 more
TL;DR: A new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts are presented, designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience.
Posted Content
Experience Replay for Continual Learning
TL;DR: This work shows that using experience replay buffers for all past events with a mixture of on- and off-policy learning can still learn new tasks quickly yet can substantially reduce catastrophic forgetting in both Atari and DMLab domains, even matching the performance of methods that require task identities.
Proceedings Article
Experience Replay for Continual Learning
TL;DR: In this paper, a replay-based method is proposed to reduce catastrophic forgetting in multi-task reinforcement learning, which leverages off-policy learning and behavioral cloning from replay to enhance stability, as well as onpolicy learning to preserve plasticity.
Proceedings ArticleDOI
A Recurrent Variational Autoencoder for Human Motion Synthesis
TL;DR: A novel generative model of human motion that can be trained using a large motion capture dataset, and allows users to produce animations from high-level control signals that can predict the movements of the human body over long horizons more accurately than state-of-theart methods.