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. https://t.co/azXUCByeKk pic.twitter.com/q4GnF3DIYr
— DeepMind (@DeepMindAI) November 4, 2019
from Twitter https://twitter.com/DeepMindAI
November 04, 2019 at 06:11AM
via IFTTT
No comments:
Post a Comment