Metadata-Version: 2.1
Name: drlgeb
Version: 0.0.1
Summary: A sample but effective drl lib.
Home-page: https://github.com/mikuh/drlgeb
Author: geb
Author-email: 853934146@qq.com
License: UNKNOWN
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
        ```shell script
        pip install drlgeb
        ```
        
        ## Get start
        
        #### A3C
        ```python
        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)
        
        ```
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
