Simple
This environment is part of the mpe environments. Please read that page first for general information.
| Name | Value |
|---|---|
| Actions | Discrete |
| Agents | 1 |
| Parallel API | True |
| Manual Control | No |
| Action Shape | (5) |
| Action Values | Discrete(5) |
| Observation Shape | (4) |
| Observation Values | (-inf,inf) |
| Import | from pettingzoo.mpe import simple_v2 |
| Agents | agents= [agent_0] |
Agent Environment Cycle
Simple
In this environment a single agent sees a landmark position and is rewarded based on how close it gets to the landmark (Euclidian distance). This is not a multiagent environment, and is primarily intended for debugging purposes.
Observation space: [self_vel, landmark_rel_position]
Arguments
simple.env(max_cycles=25)
max_cycles: number of frames (a step for each agent) until game terminates