🕹 Edge#91: Model-Free RL; Atari57 that outperformed humans; and DeepMind's OpenSpiel, an RL framework for games
In this issue:
we discuss what is model-free reinforcement learning (MFRL);
we explore Agent57, an MFRL agent that outperformed the standard human benchmark on all 57 Atari games;
we explain DeepMind’s OpenSpiel – an open-source reinforcement learning framework for games.
💡 ML Concept of the Day: What is Model-Free Reinforcement Learning?