|
@DeepMind | |||||
|
Out-of-sample generalisation of memory in deep reinforcement learning agents: we demonstrate how two different kinds of memory help out-of-distribution generalisation, and propose a memory task suite. arxiv.org/abs/1910.13406 pic.twitter.com/q4GnF3DIYr
|
||||||
|
||||||
|
DeepMind
@DeepMind
|
4. stu |
|
Memory Task Suite webpage: sites.google.com/corp/view/memo…
Authors: Meire Fortunato, Melissa Tan, Ryan Faulkner, @zergylord, Adrià Badia, Gavin Buttimore, @bigblueboo, @jzl86, @BlundellCharles
|
||
|
|
||