solve_the_spire VS bomberman

https://github.com/DevJac/solve_the_spire

I stretched the truth a bit, I'm actually doing something like "hierarchical model-free reinforcement learning", even so, figuring out how to break the game down to create a hierarchy of agents is a lot of work. Basically, the AI is composed of about 8 different traditional RL agents (neural networks), each deciding a different thing. One chooses which cards to draft, one chooses which actions to take in combat, one chooses which path to take on the map, etc.

It shows definite signs of improvement, but has only reached a point where it can beat the act 1 boss about 50% of the time. I think that is its limit right now. I'm doing policy gradient which is very sample inefficient. I'm going to implement soft-actor-critic and see if it can do better with better sample efficiency.

And to reiterate my original point, I think each developer only has one or two reverse engineering attempts in them. I might otherwise be interested in this AI competition, but reverse engineering the environment to create my own model is just too daunting, I'm so burned out on it already.

I made a similar game a few years ago while in undergrad: https://github.com/aybabtme/bomberman

Nowhere as polished or ambitious, but it just came to mind. Bomberman is a fun game!