Source code for pettingzoo.atari.warlords.warlords
# noqa: D212, D415
"""
# Warlords
```{figure} atari_warlords.gif
:width: 140px
:name: warlords
```
This environment is part of the <a href='..'>Atari environments</a>. Please read that page first for general information.
| Import | `from pettingzoo.atari import warlords_v3` |
|----------------------|----------------------------------------------------------|
| Actions | Discrete |
| Parallel API | Yes |
| Manual Control | No |
| Agents | `agents= ['first_0', 'second_0', 'third_0', 'fourth_0']` |
| Agents | 4 |
| Action Shape | (1,) |
| Action Values | [0,5] |
| Observation Shape | (210, 160, 3) |
| Observation Values | (0,255) |
Four player last man standing!
Defend your fortress from the ball and hit it towards your opponents.
When your fortress falls, you receive -1 reward and are done. If you are the last player standing, you receive +1 reward.
[Official wizard_of_wor manual](https://atariage.com/manual_html_page.php?SoftwareLabelID=598)
#### Environment parameters
Environment parameters are common to all Atari environments and are described in the [base Atari documentation](../atari) .
### Action Space (Minimal)
In any given turn, an agent can choose from one of 6 actions.
| Action | Behavior |
|:---------:|-----------|
| 0 | No operation |
| 1 | Fire |
| 2 | Move up |
| 3 | Move right |
| 4 | Move left |
| 5 | Move down |
### Version History
* v3: Minimal Action Space (1.18.0)
* v2: Breaking changes to entire API (1.4.0)
* v1: Fixes to how all environments handle premature death (1.3.0)
* v0: Initial versions release (1.0.0)
"""
import os
from glob import glob
from pettingzoo.atari.base_atari_env import (
BaseAtariEnv,
base_env_wrapper_fn,
parallel_wrapper_fn,
)
[docs]
def raw_env(**kwargs):
name = os.path.basename(__file__).split(".")[0]
parent_file = glob(
os.path.join(os.path.dirname(os.path.dirname(__file__)), name + "*.py")
)
version_num = parent_file[0].split("_")[-1].split(".")[0]
name = name + "_" + version_num
return BaseAtariEnv(
game="warlords", num_players=4, mode_num=None, env_name=name, **kwargs
)
env = base_env_wrapper_fn(raw_env)
parallel_env = parallel_wrapper_fn(env)