DRL Wizard
DRL Wizard is a clean, modular Deep Reinforcement Learning toolkit for training, comparing, and understanding modern RL algorithms. It supports multiple environments, multiple algorithms, real-time monitoring, and a unified workflow through a FastAPI backend and Streamlit UI.
🚀 Features
- Algorithms: PPO, TRPO, DQN, Double DQN, Dueling DQN, SAC (more coming)
- Environments: Gymnasium, Atari (ALE), image-based & multi-discrete action spaces
- Architecture: FastAPI backend, Streamlit UI, SQLAlchemy storage, Pydantic configs
- Experiment Tools: concurrent jobs, graceful stop, NDJSON logs, TensorBoard, job archives
- Extensible: easy to add algorithms, envs, or visualization components
📦 Installation
Basic
pip install drl-wizard
UI + Dev tools:
pip install drl-wizard[ui,dev]
🖥️ Running
- Running the UI & Backend:
drl-wizard-run
- Running Backend:
drl-wizard-api
- Running UI:
drl-wizard-ui
📝 Notes
-
drl-wizard-run launches the full platform.
-
Extras ([ui], [dev]) include Streamlit, and development dependencies.
1 maintainer
Metadata
1 maintainer
Release files for drl-wizard 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| drl_wizard-0.1.3.tar.gz | 108.2 kB | Without provenance | Details for drl_wizard-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| drl_wizard-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for drl_wizard-0.1.3-py3-none-any.whl |
Total release size: 264.2 kB
Release files / drl_wizard-0.1.3.tar.gz
| Download URL | drl_wizard-0.1.3.tar.gz |
|---|---|
| Size | 108.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1790c650089afdc47814f97ebd591c17fa7b1411320ec5df8271adb9a81efbbc
|
|
BLAKE2b-256 checksum How to use checksums |
85d57c3c0da7f5ed45a0332152204f352ffe08ec346e13395a4250198bc84e01
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / drl_wizard-0.1.3-py3-none-any.whl
| Download URL | drl_wizard-0.1.3-py3-none-any.whl |
|---|---|
| Size | 155.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
49f33e80be3300d79c5adb549ee73468bb607e04002054283b62c97fab7c036a
|
|
BLAKE2b-256 checksum How to use checksums |
d7511402d4e163b0089f740090ecec7e7aa8348e8adba24abeceb3220c982bed
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for drl-wizard 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
