Emtombed: Competitive

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

Import	from pettingzoo.atari import entombed_competitive_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)

Entombed’s competitive version is a race to last the longest.

You need to quickly navigate down a constantly generating maze you can only see part of. If you get stuck, you lose. Note you can easily find yourself in a dead-end escapable only through the use of rare power-ups. In addition, there dangerous zombies lurking around to avoid. Whenever your opponent dies, you get +1 reward, and your opponent gets -1 reward.

Official Entombed 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: Breaking changes to entire API, fixed Entombed rewards (1.4.0)

• v1: Fixes to how all environments handle premature death (1.3.0)

• v0: Initial versions release (1.0.0)

Usage

AEC

from pettingzoo.atari import entombed_competitive_v3

env = entombed_competitive_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 entombed_competitive_v3

env = entombed_competitive_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.entombed_competitive.entombed_competitive.raw_env(**kwargs)