Hi David,

The method described in Part 0 wouldn’t work well for CartPole. The problem is that the relationship between the state and action spaces is much more complex, and using the one-step updating described in Part 0 would fail to learn the dynamics of this space robustly. More advanced methods like DQN (which I describe in Part 4) would help in this case, but would still take awhile to learn due to the one-step nature.

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