Along with @maciejwolczyk we’ve been training a neural network that learns how to play NetHack, an old roguelike game, that looks like in the screenshot. Recently, something unexpected happened.
Along with @maciejwolczyk we’ve been training a neural network that learns how to play NetHack, an old roguelike game, that looks like in the screenshot. Recently, something unexpected happened.
Their problem:
The model wasn’t trained on a full moon. They had a system to set up the environment for replicable results but it didn’t include modifying the system time.
Their problem was not understanding the game ;)
That reminds me of The case of the 500-mile email
That was the first thing I thought of.