Michael Dann
YOU?
Author Swipe
View article: SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning
SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning Open
Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete mod…
View article: NOTE ON CONVENTIONS
NOTE ON CONVENTIONS Open
The editors have imposed spelling, citation style and other conventions of Edinburgh University Press on all contributions with two major exceptions, both in accordance with usual practice in premodern studies.First, Arabic and Persian are…
View article: ACKNOWLEDGEMENTS
ACKNOWLEDGEMENTS Open
Studies betweenArabophone and Western Scholarship', convened at Pembroke College, Oxford, 9-10 January 2017, thanks to a gift from Brian Wilson (d.2019), Old