Bomberman Reinforcement Learning

Agents:

coin_agent: Simple Q-table based agent only collecting coins
pca_trainer: Used to collect as many game states as possible for PCA training
strong_agent: Our final agent. Using multiple multi-layer perceptron regressors

Name		Name	Last commit message	Last commit date
Latest commit History 45 Commits
agent_code		agent_code
assets		assets
figs		figs
logs		logs
replays		replays
screenshots		screenshots
.gitignore		.gitignore
Dockerfile		Dockerfile
README.md		README.md
agents.py		agents.py
analysis.ipynb		analysis.ipynb
environment.py		environment.py
events.py		events.py
fallbacks.py		fallbacks.py
items.py		items.py
main.py		main.py
matplotlibrc		matplotlibrc
replay.py		replay.py
settings.py		settings.py
submission.sh		submission.sh
test.py		test.py

Provide feedback