DeepMind’s MEME Agent Achieves Human-level Atari Game Performance 200x Faster Than Agent57

In the new paper Human-level Atari 200x Faster, a DeepMind research team applies a set of diverse strategies to Agent57, with their resulting MEME (Efficient Memory-based Exploration) agent surpassing the human baseline on all 57 Atari games in just 390 million frames — two orders of magnitude faster than Agent57.

ai artificial intelligence atari games deepmind deep-neural-networks game human machine learning machine learning & data science meme ml performance reinforcement learning research technology