Skip to main content

Gymnasium environments and wrappers published by ART team. It is a part of ART-Framework(TM) and ART-Gym(TM).

Project description

ART Gym Environment Package

ART environments and wrappers for Gymnasium.

Environments

This repository hosts the examples that are shown on the environment creation documentation.

  • GridWorldEnv: Simplistic implementation of gridworld environment

Wrappers

This repository hosts the examples that are shown on wrapper documentation.

  • ClipReward: A RewardWrapper that clips immediate rewards to a valid range
  • DiscreteActions: An ActionWrapper that restricts the action space to a finite subset
  • RelativePosition: An ObservationWrapper that computes the relative position between an agent and a target
  • ReacherRewardWrapper: Allow us to weight the reward terms for the reacher environment

Contributing

If you would like to contribute, follow these steps:

  • Fork this repository
  • Clone your fork
  • Set up pre-commit via pre-commit install

PRs may require accompanying PRs in the documentation repo.

Installation

To install your new environment, run the following commands:

cd artgym_env
pip install -e .

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

artgym_env-0.0.2.tar.gz (23.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

artgym_env-0.0.2-py3-none-any.whl (23.5 MB view details)

Uploaded Python 3

File details

Details for the file artgym_env-0.0.2.tar.gz.

File metadata

  • Download URL: artgym_env-0.0.2.tar.gz
  • Upload date:
  • Size: 23.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.18

File hashes

Hashes for artgym_env-0.0.2.tar.gz
Algorithm Hash digest
SHA256 e9109d23a80da1c6cb140d5f2304b910ada3d0c8138763917c4670e292e2ff05
MD5 05e05399d7ec29db3020fb05a41f5b5c
BLAKE2b-256 8819d7f98fb846e8d12c327f8adf8efc36e8d7e524f8b063e182e0e75c14c6ac

See more details on using hashes here.

File details

Details for the file artgym_env-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: artgym_env-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 23.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.18

File hashes

Hashes for artgym_env-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 98b4775953d55d1f0f759bdc01cae357c49e0572ebfb53c1f257f55a8250a587
MD5 f3fd99654d2f91265159efa5b4c55c8b
BLAKE2b-256 232a97ca5360ceac7dd1012681055a56b786e9cd4d9a3d7fe4a5b25f9200f238

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page