Pong¶
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 |
2 |
Action Shape |
(1,) |
Action Values |
[0,5] |
Observation Shape |
(210, 160, 3) |
Observation Values |
(0,255) |
Classic two player competitive game of timing.
Get the ball past the opponent.
Scoring a point gives you +1 reward and your opponent -1 reward.
Serves are timed: If the player does not serve within 2 seconds of receiving the ball, they receive -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 Pong are
pong_v3.env(num_players=2)
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 right |
3 |
Move left |
4 |
Fire right |
5 |
Fire left |
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 basketball_pong_v3
env = basketball_pong_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 basketball_pong_v3
env = basketball_pong_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()