Simple Adversary

environment gif

This environment is part of the mpe environments. Please read that page first for general information.

Name Value
Actions Discrete
Agents 3
Parallel API True
Manual Control No
Action Shape (5)
Action Values Discrete(5)
Observation Shape (8),(10)
Observation Values (-inf,inf)
Import from pettingzoo.mpe import simple_adversary_v1
Agents agents= [adversary_0, agent_0,agent_1]

Agent Environment Cycle

environment aec diagram

Simple Adversary

In this environment, there is 1 adversary (red), N good agents (green), N landmarks (default N=2). All agents observe the position of landmarks and other agents. One landmark is the ‘target landmark’ (colored green). Good agents are rewarded based on how close the closest one of them is to the target landmark, but negatively rewarded based on how close the adversary is to the target landmark. The adversary is rewarded based on distance to the target, but it doesn’t know which landmark is the target landmark. All rewards are unscaled Euclidian distance (see main MPE documentation for average distance). This means good agents have to learn to ‘split up’ and cover all landmarks to deceive the adversary.

Agent observation space: [self_pos, self_vel, goal_rel_position, landmark_rel_position, other_agent_rel_positions]

Adversary observation space: [landmark_rel_position, other_agents_rel_positions]

Agent action space: [no_action, move_left, move_right, move_down, move_up]

Adversary action space: [no_action, move_left, move_right, move_down, move_up]

Arguments

simple_adversary.env(N=2, max_frames=25)

N: number of good agents and landmarks

max_frames: number of frames (a step for each agent) until game terminates