Quadrapong¶
This environment is part of the Atari environments. Please read that page first for general information.
Import |
|
|---|---|
Actions |
Discrete |
Parallel API |
Yes |
Manual Control |
No |
Agents |
|
Agents |
4 |
Action Shape |
(1,) |
Action Values |
[0,5] |
Observation Shape |
(210, 160, 3) |
Observation Values |
(0,255) |
Four player team battle.
Each player controls a paddle and defends a scoring area. However, this is a team game, and so two of the 4 scoring areas belong to the same team. So a given team must try to coordinate to get the ball away from their scoring areas towards their opponent’s.
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 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¶
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 6 actions.
Action |
Behavior |
|---|---|
0 |
No operation |
1 |
Fire |
2 |
Move up |
3 |
Move right |
4 |
Move left |
5 |
Move down |
Version History¶
v4: Minimal Action Space (1.18.0)
v3: No action timer (1.9.0)
v1: Breaking changes to entire API (1.4.0)
v2: Fixed quadrapong rewards (1.2.0)
v0: Initial versions release (1.0.0)
Usage¶
AEC¶
from pettingzoo.atari import quadrapong_v4
env = quadrapong_v4.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 quadrapong_v4
env = quadrapong_v4.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()