Our latest work allows agents to reach human-level on Quake III Arena Capture the Flag through new multi-agent RL techniques: populations of agents learning their own internal reward signal and operating at multiple timescales https://t.co/phXmGFoIkK pic.twitter.com/P3KW908ljq
— DeepMind (@DeepMindAI) July 3, 2018
from Twitter https://twitter.com/DeepMindAI
July 03, 2018 at 09:03AM
via IFTTT
No comments:
Post a Comment