Simple Spread#


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


from pettingzoo.mpe import simple_spread_v2



Parallel API


Manual Control



agents= [agent_0, agent_1, agent_2]



Action Shape


Action Values

Discrete(5)/Box(0.0, 1.0, (5))

Observation Shape


Observation Values


State Shape


State Values


This environment has N agents, N landmarks (default N=3). At a high level, agents must learn to cover all the landmarks while avoiding collisions.

More specifically, all agents are globally rewarded based on how far the closest agent is to each landmark (sum of the minimum distances). Locally, the agents are penalized if they collide with other agents (-1 for each collision). The relative weights of these rewards can be controlled with the local_ratio parameter.

Agent observations: [self_vel, self_pos, landmark_rel_positions, other_agent_rel_positions, communication]

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


simple_spread_v2.env(N=3, local_ratio=0.5, max_cycles=25, continuous_actions=False)

N: number of agents and landmarks

local_ratio: Weight applied to local reward and global reward. Global reward weight will always be 1 - local reward weight.

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

continuous_actions: Whether agent action spaces are discrete(default) or continuous