Foozpong

../../../_images/atari_foozpong.gif

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

Import

from pettingzoo.atari import foozpong_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 team battle.

Get the ball past your opponent’s defenders to the scoring area. Like traditional foozball, the board has alternating layers of paddles from each team between the goal areas. To succeed at this game, the two players on each side must coordinate to allow the ball to be passed between these layers up the board and into your opponent’s scoring area. Specifically, first_0 and third_0 are on one team and second_0 and fourth_0 are on the other.

Scoring a point gives your team +1 reward and your opponent’s team -1 reward.

Serves are timed: If the player does not serve within 2 seconds of receiving the ball, their team receives -1 points, and the timer resets. This prevents one player from indefinitely stalling the game, but also means it is no longer a purely zero sum game.

Official Video Olympics manual

Environment parameters

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

Parameters specific to Foozpong are

foozpong_v3.env(num_players=4)

num_players: Number of players (must be either 2 or 4)

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: No action timer (1.9.0)

  • v1: Breaking changes to entire API (1.4.0)

  • v0: Initial versions release (1.0.0)

Usage

AEC

from pettingzoo.atari import foozpong_v3

env = foozpong_v3.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 foozpong_v3

env = foozpong_v3.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.foozpong.foozpong.raw_env(num_players=4, **kwargs)[source]