Skip to main content

3D ConnectX for OpenAI Gym.

Project description

3d-connect4-gym

BuildStatus PackageVersion PythonVersion Stable Format License

pattern1.gif

3D connectX repository, developed for the OpenAI Gym format.

Installation

The preferred installation of 3d-connectX-env is from pip:

pip install 3d-connectX-env

Usage

Python

from gym_3d_connectX.envs import AnyNumberInARow3dEnv

env = AnyNumberInARow3dEnv()
env.reset()

env.utils.win_reward = 100
env.utils.draw_penalty = 50
env.utils.lose_penalty = 100
env.utils.could_locate_reward = 10
env.utils.couldnt_locate_penalty = 10
env.utils.time_penalty = 1
env.player = 1
actions = [0, 0, 1, 1, 2, 2, 4, 4, 0, 0, 1, 1, 2, 2, 0, 3]

for action in actions:
    obs, reward, done, info = env.step(action)
    env.render(mode="plot")

Environments

The environments only send reward-able game-play frames to agents; No cut-scenes, loading screens, etc. are sent to an agent nor can an agent perform actions during these instances.

Environment: 3d-connectX-v0

Factor at initialization.

Key Type Description
num_grid int Length of a side.
num_win_seq int The number of sequence necessary for winning.
win_reward float The reward agent gets when win the game.
draw_penalty float The penalty agent gets when it draw the game.
lose_penalty float The penalty agent gets when it lose the game.
couldnt_locate_penalty float The penalty agent gets when it choose the location where the stone cannot be placed.
could_locate_reward float The additional reward for agent being able to put the stone.
time_penalty float The penalty agents gets along with timesteps.
first_player int Define which is the first player.

Step

Info about the rewards and info returned by the step method.

Key Type Description
turn int The number of the player at this step
winner int Value of the player on the winning side
is_couldnt_locate bool In this step the player chooses where to place the stone.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

3d-connectX-env-1.0.0.tar.gz (3.9 kB view hashes)

Uploaded source

Built Distribution

3d_connectX_env-1.0.0-py3-none-any.whl (3.5 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page