> For the complete documentation index, see [llms.txt](https://www.mlcompendium.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.mlcompendium.com/machine-learning/incremental-learning-1.md).

# Reinforcement Learning

## Introduction

1. [Reinforcement Learning: An Introduction second edition WIP](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf) & completed [book](http://incompleteideas.net/book/RLbook2020.pdf)
2. Vidhya on [Getting ready for AI based gaming agents – Overview of Open Source Reinforcement Learning Platforms](https://www.analyticsvidhya.com/blog/2016/12/getting-ready-for-ai-based-gaming-agents-overview-of-open-source-reinforcement-learning-platforms/)
3. Vidhya on [Simple Beginner’s guide to Reinforcement Learning & its implementation](https://www.analyticsvidhya.com/blog/2017/01/introduction-to-reinforcement-learning-implementation/)
4. ZipRecruiter on [Classifying Job Titles With Noisy Labels Using REINFORCE ](https://medium.com/@ziprecruiter.engineering/classifying-job-titles-with-noisy-labels-using-reinforce-ce1a4bde05e2)- Fine-grained job title classification with noisy labels using the REINFORCE algorithm and multi-task learning

   -> this article has a very nice trick in adding a reward component to the loss function in order to mitigate for unbalanced class label problem, instead of the usual balancing.
5. David Silver - [Home Page](https://www.davidsilver.uk/teaching/) - [1](https://www.youtube.com/watch?v=2pWv7GOvuf0) [2](https://www.youtube.com/watch?v=lfHX2hHRMVQ) [3](https://www.youtube.com/watch?v=Nd1-UUMVfz4) [4](https://www.youtube.com/watch?v=PnHCvfgC_ZA) [5](https://www.youtube.com/watch?v=0g4j2k_Ggc4) [6](https://www.youtube.com/watch?v=UoPei5o4fps) [7](https://www.youtube.com/watch?v=KHZVXao4qXs) [8](https://www.youtube.com/watch?v=ItMutbeOHtc) [9](https://www.youtube.com/watch?v=sGuiWX07sKw) [10](https://www.youtube.com/watch?v=kZ_AUmFcZtk)\
   ![](/files/n5qY5uZChFsGLQDAi6ER)
6. [Sequential Decision Analytics and Modeling](https://castle.princeton.edu/sdamodeling/) book

### **Q-LEARN**

* **Markov chain problem, (state, action, new state, reward)**
* **Lots of Exploration in the beginning, then exploitation** 
* **Returns optimal policy.**
* **Refer to youtube** [**here**](https://www.youtube.com/watch?v=9m_6q_KECTk)

### **Deep Learning**

1. [A review paper about RL in DL](https://arxiv.org/pdf/1701.07274.pdf)
2. [deep Q-learning](https://www.analyticsvidhya.com/blog/2019/04/introduction-deep-q-learning-python/)
3. Pytorch
   1. [DQN](https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html)
   2. [PPO](https://pytorch.org/tutorials/intermediate/reinforcement_ppo.html)
   3. [Mario example](https://pytorch.org/tutorials/intermediate/mario_rl_tutorial.html)

## RLHF

1. [illustrated RLHF by Huggingface](https://huggingface.co/blog/rlhf)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://www.mlcompendium.com/machine-learning/incremental-learning-1.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.