The CRN represent causal models using continuous representations and hence could scale much better with the number of variables.
The emergence of powerful artificial intelligence is defining new research directions in neuroscience.
no code implementations • 8 May 2019 • Pedro A. Ortega, Jane. X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
Multi-agent cooperation is an important feature of the natural world.
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins.
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
Much of human knowledge sits in large databases of unstructured text.