Factual package intelligence from PyPI

effective-horizon 0.1.3 package intelligence

Code for the NeurIPS 2023 paper "Bridging RL Theory and Practice with the Effective horizon" and the ICLR 2024 paper "The Effective Horizon Explains Deep RL Performance in Stochastic Environments".

pip install effective-horizon

Current version
0.1.3
Python requirement
>=3.8
License
MIT License
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
135.1 KiB
Release history
3 releases with files
Median release cadence
0 days

effective-horizon dependencies

PyPI declares 28 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. sacred >=0.8.2
  2. torch >=1.10.0
  3. minigrid <2.3,>=2.2
  4. gymnasium
  5. numpy >=1.20.3
  6. scipy >=1.8
  7. autorom >=0.4.2
  8. GPUtil >=1.4.0
  9. procgen >=0.10.7
  10. torchvision >=0.11.1
  11. tensorflow-probability
  12. tqdm
  13. opencv-python
  14. tensorboard

The compact report shows 25 of 28 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

effective-horizon publishes 1 wheel and 1 source archive for version 0.1.3. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.8, 3.9.

Release activity and sources

PyPI lists 3 releases with files. The first dated release is ; 3 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .