[foo12bar]

But if not the snake could go into an infinite loop, never growing, never eating.

[ziofill]

Why? It should get the reward for getting longer, but not for getting longer quicker

[foo12bar]

Because the sessions would last forever. Think of a 1 or 2 length snake, figuring out that left down up right over and over again doesn't lose any points. You're now trapped in a local minimum. You need to make the AI get impatient (lose points) or it'll never learn.

[ziofill]

I see what you are saying but then wouldn’t it miss out on the best strategies, which do require patience and not going straight for the apple?

[foo12bar]

Maybe you could make it lose points for repeating a board state, I guess.

[ziofill]

Ah yes that’s probably the right approach