Home

The reinforcement algorithm repository consists of a number of different items that may be used independently of one another. Since there is a plethora of different ideas behind each type of RL algorithms, it is really important that one incorporates all these ideas into smaller manageable sets. This wikipedia will work as both a tutorial as well as something that one can use to get started on using these algorithms in a meaningful manner.

Overview

1. Getting Started
   1. Installation
   2. Structure of the repo
2. User Guide
   1. Environments
   2. Memory Buffers
   3. Utilities (qNetwork, )
   4. Agents (DQN, Double DQN)
   5. Testing Modules
3. Generating the API reference
   1. API reference
   2. Module Index
   3. Entire Index
4. Contributing

Remember that this is a work in progress and something that I do in my spare time. I make updates as and when I find time away form my other activities. If there are things that you would like to see implemented, please let me know by opening an issue.