Learning-AI

Human-level control through deep reinforcement learning

01/06/2019

tl;dr: the founding paper of DQN

Key ideas

Notes/Questions

Nevertheless, games demanding more temporally extended planning strategies still constitute a major challenge for all existing agents including DQN (for example, Montezuma’s Revenge).

Overall impression: fill this out last; it should be a distilled, accessible description of your high-level thoughts on the paper.