https://github.com/DanielAvdar/prob-spaces

https://github.com/DanielAvdar/prob-spaces

Last synced: 5 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/DanielAvdar/prob-spaces
• Owner: DanielAvdar
• License: mit
• Created: 2025-03-16T19:06:45.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2025-04-20T19:58:23.000Z (6 months ago)
• Last Synced: 2025-04-22T19:47:55.951Z (6 months ago)
• Language: Python
• Size: 5.81 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-opensource-israel - prob-spaces - Probability Distributions from Gymnasium Spaces. (Projects by main language / python)

README

          
# prob-spaces: Probability Distributions from Gymnasium Spaces

[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/prob-spaces)](https://pypi.org/project/prob-spaces/)

[![version](https://img.shields.io/pypi/v/prob-spaces)](https://img.shields.io/pypi/v/prob-spaces)

[![License](https://img.shields.io/:license-MIT-blue.svg)](https://opensource.org/licenses/MIT)

![OS](https://img.shields.io/badge/ubuntu-blue?logo=ubuntu)

![OS](https://img.shields.io/badge/win-blue?logo=windows)

![OS](https://img.shields.io/badge/mac-blue?logo=apple)

[![Tests](https://github.com/DanielAvdar/prob-spaces/actions/workflows/ci.yml/badge.svg)](https://github.com/DanielAvdar/prob-spaces/actions/workflows/ci.yml)

[![Code Checks](https://github.com/DanielAvdar/prob-spaces/actions/workflows/code-checks.yml/badge.svg)](https://github.com/DanielAvdar/prob-spaces/actions/workflows/code-checks.yml)

[![codecov](https://codecov.io/gh/DanielAvdar/prob-spaces/graph/badge.svg?token=N0V9KANTG2)](https://codecov.io/gh/DanielAvdar/prob-spaces)

[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)

![Last Commit](https://img.shields.io/github/last-commit/DanielAvdar/prob-spaces/main)

**prob-spaces** is a Python package that allows you to create probability distributions from Gymnasium spaces.

It provides a simple and intuitive interface for working with various probability spaces in reinforcement learning

environments.

Key Features:

* Create probability distributions directly from Gymnasium spaces

* Support for common space types: Discrete, MultiDiscrete, Box, and Dict

* Seamless integration with PyTorch for sampling and computing log probabilities

* Support for masking operations to constrain valid actions

## Installation

### From PyPI

To install prob-spaces from PyPI:

```bash

pip install prob-spaces

```

### GPU Support

prob-spaces uses PyTorch, which can be installed with CUDA support for GPU acceleration.

The package configuration includes a PyTorch CUDA 12.4 index. To use a different CUDA version,

you may need to modify the PyTorch installation separately.

## Example Usage

Here's a simple example of how to use prob-spaces:

```python

import gymnasium as gym

import torch as th

from prob_spaces.converter import convert_to_prob_space

# Create a Gymnasium space

action_space = gym.spaces.Discrete(5)

# Convert to a probability space

prob_space = convert_to_prob_space(action_space)

# Create a probability distribution

probs = th.ones(5)  # Uniform distribution

dist = prob_space(probs)

# Sample from the distribution

action = dist.sample()

# Compute log probability

log_prob = dist.log_prob(action)

```

## Documentation

[Documentation](https://prob-spaces.readthedocs.io/en/latest/) is available online and provides detailed information on how to use the package, including examples and API references.