This is highly significant because it was one of the games that the Atari games ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		alexcnwy on July 4, 2018 \| parent \| context \| favorite \| on: Learning ‘Montezuma’s Revenge’ from a single demon... This is highly significant because it was one of the games that the Atari games that the original Deep Q learning model could not beat.

sherjilozair on July 4, 2018 [–]

DQN is solving a model-free RL problem. This method is not. You're not allowed to reset states in model-free RL. If you have access to the model/simulator which allows you to reset, you might as well use a model-based method like MCTS.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact