A sample but effective drl lib.
Project description
drlgeb
A sample DRL lib use tf.keras and gym. Just writing ...
Now just implement the batch a3c, other algorithms will be updated in the future.
Requirement
- Linux/windows/osx
- python3.8
- tensorflow2.4
- gym[atari]
- numpy
Installation
pip install drlgeb
Get start
A3C
from drlgeb.ac import A3C
env_id = "SpaceInvaders-v0"
agent = A3C(env_id=env_id)
# train
agent.learn()
# test
model_path = "..."
agent.play(episodes=5, model_path=model_path)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
drlgeb-0.0.1.tar.gz
(13.6 kB
view details)
Built Distribution
drlgeb-0.0.1-py3-none-any.whl
(18.1 kB
view details)
File details
Details for the file drlgeb-0.0.1.tar.gz.
File metadata
- Download URL: drlgeb-0.0.1.tar.gz
- Upload date:
- Size: 13.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.0.0.post20201207 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 4334e87690f4418200769898e529c2350675270bfe4651c0011a60ae030b0cf6 |
|
| MD5 | 10d2d701d4750d5ef3798d7688403901 |
|
| BLAKE2b-256 | ada4d1d93e5f2bf96f42e8cf3cfc41ab2d6b30ecf930996184b3a2117cceee45 |
File details
Details for the file drlgeb-0.0.1-py3-none-any.whl.
File metadata
- Download URL: drlgeb-0.0.1-py3-none-any.whl
- Upload date:
- Size: 18.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.0.0.post20201207 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 4a794ee2780cd2c7fac0dbeb272e7a9ef1682abaed11546d45f51fd1fc1ba1cc |
|
| MD5 | 76b59b2bb4830ff53cf63951fdbc7c8a |
|
| BLAKE2b-256 | 36dff89ff2c41ee125627a542f29f89cd756d64d6d625e1403b56f3b046eb754 |
