MultiAgentRL

Codebase for TTIC project

On Spread:

  • Q_Learning.py has the code for the Independent agents trained with Deep Q-learning
  • Q_LearningParallel is the same but using the parallel learning environment / API.
  • ActorCritic.py has the code for our actor-critic implementation
  • simple.py has the code for the VDN (on spread)
  • QMIX_FINAL has the code for the QMIX implementation

Link notebook here: