My impression on DeepMind's Deep-Q RL for learning Atari games paper is that it uses the same model to learn to play multiple different games at the same time. I wonder how did the RL agent learn in such a setting. In particular, when the game environment changed, how does the agent know the corresponding objective to achieve in that specific game? Is there a prompt to tell the agent what game it is currently in before training/evaluation? Or the agent can infer what is the goal simply by observing the feature from the environment (e.g. by observing blocks of bricks it can infer it needs to break all of them, can by observing there is a controllable vehicle its knows it is probably a racing game)?

  • 1
    $\begingroup$ Does this answer the question? ai.stackexchange.com/questions/2190/… $\endgroup$
    – maxy
    Commented Oct 30, 2022 at 11:38
  • $\begingroup$ yes. thank you so much! $\endgroup$
    – Sam
    Commented Oct 30, 2022 at 13:08


You must log in to answer this question.

Browse other questions tagged .