Deep Reinforcement Learning Repository
This is the repository for learning the fundamental of Reinforcement Learning - a paradigm of machine learning that deals with how software agents carry out the task efficiently based on the environment. The exercises are provided by Udacity courses, and all the algorithm are implemented in Pytorch (which is covered by a free licence (Modified BSD license)).
List of Folders:
-
Exercise_I_Navigation_Control: Project Navigation for Udacity's Deep Reinforcement Learning courses.
-
Exercise_II_Continuous_Control: Project Continuous Control for Udacity's Deep Reinforcement Learning courses.
-
Exercise_III_Collaboration_and_Competition: Project Collaboration and Competition for Udacity's Deep Reinforcement Learning courses.
-
Finance: Udacity's example of using Deep Reinforcement Learning on trading in the stock market.
The environment for the agents are listed belows:
- OpenAI Gym: Repository, Installation Guidelines
- ml-agents: Repository
The implementations were taken from Udacity's repository for the Deep Reinforcement Learning Nanodegree, which provided an state-of-the-art education about this topic. My purpose is mastering the Deep RL theory and algorithms, to further my goal as Machine Learning practitioner.
There are minor corrections on the implementations with the aim of making them easier to understand and consistent.