Skip to main content

Training environment for reinforcement learning with event-based context

Project description

image

Open The Chests Project

Open the Chests is a game that mimics the problem of situation recognition in a concurrent event-based environment. The player is confronted with a number of boxes, each one associated with a button. Pressing a button sometimes leads to a box opening, sometimes leads to nothing. The player also observes events being displayed on a screen. The goal of the player is to deduce a set of interpretable event-based rules that allow them to determine with confidence at which moment the chests can be opened.

Quick Start

Open-the-Chests is available on Pypi. To install it and all its libraries simply run:

pip install openthechests

The environment is then ready to execute by simply running the demo.py file.

Running the Demo

To test the environment, download the docs and demo.py folders. The docs folder contains examples of usage of the environment that are representative of its functioning as well as an example configuration for the demonstration. The execution of the demo.py file generates an environment using a YAML configuration file and allows you to interact with the environment manually. To run the demonstration, use the following command:

python demo.py

This will initialize the environment and start the interactive session where you can input actions to interact with the boxes.

Folder Structure

The openthechests module contains several folders and files of interest:

openthechests/
│
├── docs/
│   └── examples/
│
├── openthechests/
│   └── src/
│       ├── elements/
│       ├── utils/
│       ├── OpenTheChests.py
│       └── OpenTheChestsGym.py
│
├── demo.py
├── README.md
└── requirements.txt

Descriptions of Key Files and Folders

  • docs/: Contains documentation related to the project.

    • examples/: Example configurations and usage of the environment.
      • __init__.py: Initializes the examples module.
  • openthechests/: The main code for the environment.

    • src/: Contains the main environment elements.
      • elements/: Contains classes that define the environment elements.
      • utils/: Contains useful functions used by other modules.
      • OpenTheChests.py: Defines the core environment logic.
      • OpenTheChestsGym.py: Provides the Gym interface for the environment.
  • demo.py: Demonstration script for the environment.

  • requirements.txt: Lists the dependencies required to run the project.

  • third_parties_licences.txt: Lists the licences to apply from the dependencies

Licence

Open-the-chests applies the 3-clauses BSD licence.

Citation

If you use this training environmenet please cite:

@inproceedings{stoy24otc,
    author = {Stoyanova, Ivelina and Museux, Nicolas and Nguyen, Sao-Maï and Filliat, David},
    title = {Open the {C}hests: An {E}nvironment for {A}ctivity {R}ecognition and {S}equential {D}ecision {P}roblems {U}sing {T}emporal {L}ogic},
    year = {2024},
    month = {October},
    booktitle = {31st International Symposium on Temporal Representation and Reasoning},
    address = {Montpellier, France},
    location =	{Dagstuhl, Germany},
    publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
    series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
}

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

openthechests-0.7.4.tar.gz (178.9 kB view details)

Uploaded Source

Built Distribution

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

openthechests-0.7.4-py3-none-any.whl (33.2 kB view details)

Uploaded Python 3

File details

Details for the file openthechests-0.7.4.tar.gz.

File metadata

  • Download URL: openthechests-0.7.4.tar.gz
  • Upload date:
  • Size: 178.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for openthechests-0.7.4.tar.gz
Algorithm Hash digest
SHA256 6382ab153b2dc25c2b4efc622cd40d347de3de94148cda5c6b6e76426229a30e
MD5 109b3d40557eb569f1518cd52f6c0956
BLAKE2b-256 c06c2a8693f399b5cd867c85ad869990e85ea50b7513a1389ce3dab557153da4

See more details on using hashes here.

File details

Details for the file openthechests-0.7.4-py3-none-any.whl.

File metadata

  • Download URL: openthechests-0.7.4-py3-none-any.whl
  • Upload date:
  • Size: 33.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for openthechests-0.7.4-py3-none-any.whl
Algorithm Hash digest
SHA256 ffdc5e5f001dbd064f89a08d3d14658a8967cd5cc4a12817bbd4233bb4e01781
MD5 9aac4d9e5b9e634f8cb270a590e669f2
BLAKE2b-256 acc52d7a1b889a7aed27e023f2dd594ccbd33501a0f94c4e1670cd7811efa5a7

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