Tweeted By @DeepMind
DreamerV2, a collaboration between DeepMind, @GoogleAI and the @UofT, is the first RL agent based on a world model to achieve human-level performance on the Atari benchmark. Read more ⬇️ https://t.co/lFFuHH2Uk9
— DeepMind (@DeepMind) February 19, 2021