@googledeepmind : 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/19150.13406 • TwiCopy

Google DeepMind

@googledeepmind

+ Follow

We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.

ID: 4783690002

linkhttp://deepmind.google calendar_today19-01-2016 13:46:08

3,3K Tweet

1,1M Followers

276 Following

Google DeepMind

@googledeepmind

6 years ago

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

thumb_up_off_alt439

chat_bubble_outline1

repeat133

shareShare