Tennis¶

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

Import	`from pettingzoo.atari import tennis_v3`
Actions	Discrete
Parallel API	Yes
Manual Control	No
Agents	`agents= ['first_0', 'second_0']`
Agents	2
Action Shape	(1,)
Action Values	[0,17]
Observation Shape	(210, 160, 3)
Observation Values	(0,255)

A competitive game of positioning and prediction.

Goal: Get the ball past your opponent. Don’t let the ball get past you.

When a point is scored (by the ball exiting the area), you get +1 reward and your opponent gets -1 reward. Unlike normal tennis matches, the number of games won is not directly rewarded.

Serves are timed: If the player does not serve within 3 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 tennis manual

Environment parameters¶

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

Action Space¶

In any given turn, an agent can choose from one of 18 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
10	Fire up
11	Fire right
12	Fire left
13	Fire down
14	Fire upright
15	Fire upleft
16	Fire downright
17	Fire downleft

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 tennis_v3

env = tennis_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 tennis_v3

env = tennis_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.tennis.tennis.raw_env(**kwargs)[source]¶