J
Jane X. Wang
Researcher at Google
Publications - 28
Citations - 2207
Jane X. Wang is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 11, co-authored 18 publications receiving 1465 citations.
Papers
More filters
Posted Content
Learning to reinforcement learn
Jane X. Wang,Zeb Kurth-Nelson,Dhruva Tirumala,Hubert Soyer,Joel Z. Leibo,Rémi Munos,Charles Blundell,Dharshan Kumaran,Matthew Botvinick +8 more
TL;DR: Deep Meta-Reinforcement Learning (DML) as discussed by the authors is a meta-learning approach for reinforcement learning, where the learned RL algorithm can differ from the original one in arbitrary ways and is configured to exploit structure in the training domain.
Journal ArticleDOI
Prefrontal cortex as a meta-reinforcement learning system
Jane X. Wang,Zeb Kurth-Nelson,Dharshan Kumaran,Dhruva Tirumala,Hubert Soyer,Joel Z. Leibo,Demis Hassabis,Matthew Botvinick +7 more
TL;DR: A new theory is presented showing how learning to learn may arise from interactions between prefrontal cortex and the dopamine system, providing a fresh foundation for future research.
Journal ArticleDOI
Reinforcement Learning, Fast and Slow.
Matthew Botvinick,Samuel Ritter,Jane X. Wang,Zeb Kurth-Nelson,Charles Blundell,Demis Hassabis +5 more
TL;DR: This review describes recently developed techniques that allow deep RL to operate more nimbly, solving problems much more quickly than previous methods, and proposes that they may have rich implications for psychology and neuroscience.
Proceedings ArticleDOI
Can language models learn from explanations in context?
Andrew K. Lampinen,Ishita Dasgupta,Stephanie C.Y. Chan,Kory Matthewson,Michael Henry Tessler,Antonia Creswell,James L. McClelland,Jane X. Wang,Felix Hill +8 more
TL;DR: Investigating whether explanations of few-shot examples can help in-context learning of large LMs on challenging tasks finds that explanations can improve performance—even without tuning.
Journal ArticleDOI
Deep Reinforcement Learning and Its Neuroscientific Implications.
TL;DR: Deep reinforcement learning (RL) as discussed by the authors offers a comprehensive framework for studying the interplay among learning, representation, and decision making, offering to the brain sciences a new set of research tools and a wide range of novel hypotheses.