Flag Capture

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

Import	from pettingzoo.atari import flag_capture_v2
Actions	Discrete
Parallel API	Yes
Manual Control	No
Agents	agents= ['first_0', 'second_0']
Agents	2
Action Shape	(1,)
Action Values	[0,9]
Observation Shape	(210, 160, 3)
Observation Values	(0,255)

A battle of memory and information.

A flag is hidden on the map. You can travel through the map and check the squares in it. If it is the flag, you score a point (and your opponent is penalized). If it is a bomb, you get sent back to your starting location. Otherwise, it will give you a hint to where the flag is, either a direction or a distance. Your player needs to be able to use information from both your own search and your opponent’s search in order to narrow down the location of the flag quickly and effectively.

Official flag capture manual

Environment parameters

Environment parameters are common to all Atari environments and are described in the base Atari documentation .

Action Space (Minimal)

In any given turn, an agent can choose from one of 10 actions.

Action	Behavior
0	No operation
1	Fire
2	Move up
3	Move right
4	Move left
5	Move down
6	Move upright
7	Move upleft
8	Move downright
9	Move downleft

Version History

• v2: Minimal Action Space (1.18.0)

• v1: Breaking changes to entire API (1.4.0)

• v0: Initial versions release (1.0.0)

Usage

AEC

from pettingzoo.atari import flag_capture_v2

env = flag_capture_v2.env(render_mode="human")
env.reset(seed=42)

for agent in env.agent_iter():
    observation, reward, termination, truncation, info = env.last()

    if termination or truncation:
        action = None
    else:
        # this is where you would insert your policy
        action = env.action_space(agent).sample()

    env.step(action)
env.close()

Parallel

from pettingzoo.atari import flag_capture_v2

env = flag_capture_v2.parallel_env(render_mode="human")
observations, infos = env.reset()

while env.agents:
    # this is where you would insert your policy
    actions = {agent: env.action_space(agent).sample() for agent in env.agents}

    observations, rewards, terminations, truncations, infos = env.step(actions)
env.close()

API

class pettingzoo.atari.flag_capture.flag_capture.raw_env(**kwargs)