Hi Gabriel,

Is the issue that the reward is no longer increasing, or that it is taking increasingly longer to complete episodes. In breakout one reason for this might be that as the episode length increases, the frequency at which results are posted to the tensorboard decreases, since it is tied to the episode count.

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store