stopitcarl / multi-agent-tag Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

A Deep Q Learning approach for controllers for multi-agent systems using a well-known environment - the 2D tag game. We compare the DQN to classic hardcoded controllers assess different collaborative and competitive behaviors emerging from these approaches.

1 star 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 24 Commits
dqn_models		dqn_models
models		models
notebooks		notebooks
.gitignore		.gitignore
README.md		README.md
agent.py		agent.py
dqn.py		dqn.py
game.py		game.py
monitor.py		monitor.py
predator.py		predator.py
prey.py		prey.py
report.pdf		report.pdf
requirements.txt		requirements.txt
results.txt		results.txt
smart_agent.py		smart_agent.py
utils.py		utils.py
video.mp4		video.mp4