Skip to content

Project on multi agent reinforcement learning applied on patrolling agents

Notifications You must be signed in to change notification settings

AdrienBenamira/marl-patrolling-agents

 
 

Repository files navigation

MARL for patrolling agents

Examples after 1400 episodes of training

DDQN 2vs2 MADDPG 2vs2 DDQN 2v1 Magic Switch

Evironment

Action space

The action space is discrete. Every agent can do one of none, left, right, top, bottom.

State space

The state is perfectly known by all the agents.

The state is the 3D coordinates (x, y, z) for every agent.

About

Project on multi agent reinforcement learning applied on patrolling agents

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%