Some people claim that DQN was used to play many Atari games. But what actually happened? Was DQN trained only once (with some data from all games) or was it trained separately for each game? What was common to all those games? Only the architecture of the RL agent? Did the reward function change for each game?

  • 2
    $\begingroup$ I will provide an answer later (if nobody does it), but I think that, meanwhile, someone will provide an answer. $\endgroup$ – nbro Apr 4 '20 at 14:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.