Deep RL agents are data hungry and often learn task-specific representations. Our model learns object-centric abstractions from raw videos. This enables highly data-efficient RL and structured exploration. https://t.co/AnYkOYKRTO pic.twitter.com/yYtWH4cagX
— DeepMind (@DeepMindAI) July 1, 2019
from Twitter https://twitter.com/DeepMindAI
July 01, 2019 at 05:57AM
via IFTTT
No comments:
Post a Comment