sapai
sapai copied to clipboard
manny405
Super auto pets engine built with reinforment learning training in mind
Presently, the outcome of a battle is win lose or draw. However, outcomes of battle's with random components, for example a mosquito versus a pig(3,1)+otter(1,2) team, can have multiple outcomes....
I built an OpenAI Gym Environment on top of `sapai` that can be used for reinforcement learning. I thought I would link it here since most people here are probably...
Currently, the most natural way to deep copy is to create a state object and then instantiate a new instance from the state. Eg. `new_player = Player.from_state(orig_player.state)`. This creates a...
I've created an `Arena` for testing AIs and using the random agents is a great way to find bugs. It should be as easy as installing and running. Let me...
The compress / decompress methods provide good ways to check for equality. However, in situations where the objects do not need to be compressed (eg. unit tests), equality methods are...