A custom RL environment with C++ backend and Gymnasium wrapper.
Project description
Hybrid Shoot Environment
This C++ gymnasium compliant env is designed as a sanity check
for reinforcement learning with multiple actions with hybrid
reprisentation. There are num_enemies enemies and two actions that need
to be taken 1. Jam and 2. Shoot.
Action Space
- Jam Discrete cardonality: |num_enemies|
- Shoot Continuous dims: 2, box2D(-1,1),
[x,y]
Action Descriptions
Jamming an enemy agent stops it's attack from going through. The
effect of shooting within 'hit_radius' of an enemy depends on the
gamemode. If independent_mode=True then shooting an enemy removes
them at the end of the round. Otherwise, an enemy needs to be actively
jammed in order to be removed by shoot.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hybrid_shoot-0.1.0.tar.gz.
File metadata
- Download URL: hybrid_shoot-0.1.0.tar.gz
- Upload date:
- Size: 11.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e022fad4fa726095c20e1cdde057d739a78fa0a8c78e0ed674d66b3571358352
|
|
| MD5 |
33e85a022d87140161d68af1e27da554
|
|
| BLAKE2b-256 |
3ce75757a35446c0938235c167f694d143168c83fc37d47de2dcacd9093ae161
|
File details
Details for the file hybrid_shoot-0.1.0-cp312-cp312-win_amd64.whl.
File metadata
- Download URL: hybrid_shoot-0.1.0-cp312-cp312-win_amd64.whl
- Upload date:
- Size: 83.0 kB
- Tags: CPython 3.12, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b9105368232defa67f7a9d108d1b9fe031b64387645308a43efb8578f856e43d
|
|
| MD5 |
70953d3ee964f57c7fcddd07ae96e8fc
|
|
| BLAKE2b-256 |
e382533ea0cf509acc5f8d2f7cf3475168dddf9bf6d90e1a615d56e970ea2565
|
