Tweeted By @hardmaru
Deep RL from Pixels is moving so quickly, and the ideas that achieve large improvements are the simple ones
— hardmaru (@hardmaru) April 29, 2020
“SOTA on the DeepMind control suite, surpassing model-based (Dreamer, PlaNet, and SLAC) methods and recently proposed contrastive learning (CURL)”https://t.co/h5VDbOhnOI https://t.co/pXwk7wqEs7 pic.twitter.com/w6crfG9kfv