https://github.com/dudeperf3ct/rl_notebooks

This repo contains all the RL notebooks mentioned in blog.
https://github.com/dudeperf3ct/rl_notebooks

reinforcement-learning reinforcement-learning-excercises

Last synced: 11 months ago
JSON representation

This repo contains all the RL notebooks mentioned in blog.

• Host: GitHub
• URL: https://github.com/dudeperf3ct/rl_notebooks
• Owner: dudeperf3ct
• Created: 2020-01-26T01:03:41.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2020-01-27T01:22:03.000Z (almost 6 years ago)
• Last Synced: 2024-12-31T10:17:10.147Z (about 1 year ago)
• Topics: reinforcement-learning, reinforcement-learning-excercises
• Language: Jupyter Notebook
• Homepage: https://dudeperf3ct.github.io/
• Size: 1.89 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Blog

[![Colab](https://img.shields.io/badge/launch-Colab-orange.svg)](https://github.com/dudeperf3ct/RL_notebooks/master)

[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/dudeperf3ct/RL_Notebooks/master)

- [RL Series](https://dudeperf3ct.github.io/rl/2019/12/19/Reinforcement-Learning/)

- Implementations of different topics in RL

## Notebooks

# Tabular Methods

Tabular Methods : [Blog](https://dudeperf3ct.github.io/rl/2019/12/29/Tabular-Solution/)

Code Credits : [dennybritz](https://github.com/dennybritz/reinforcement-learning)

|:page_with_curl: Topics|:pencil2: Blog|:key: Environments|

| ------------- | :-------------: |------------- |

|:wind_chime: Dynamic Programming|[DP](https://dudeperf3ct.github.io/rl/2019/12/29/Tabular-Solution/#dynamic-programming)| [Grid World](https://colab.research.google.com/github/dudeperf3ct/RL_Notebooks/blob/master/DP/Dynamic_Programming_Grid_World.ipynb), [Frozen Lake](https://colab.research.google.com/github/dudeperf3ct/RL_Notebooks/blob/master/DP/Dynamic_Programming_FrozenLake.ipynb) |

|:rice_scene: Monte Carlo|[MC](https://dudeperf3ct.github.io/rl/2019/12/29/Tabular-Solution/#monte-carlo)|[Blackjack](https://colab.research.google.com/github/dudeperf3ct/RL_Notebooks/blob/master/MC/Monte_Carlo_Blackjack.ipynb) |

|:high_brightness: TD Learning|[TD](https://dudeperf3ct.github.io/rl/2019/12/29/Tabular-Solution/#td-learning)| [Cliff Walking](https://colab.research.google.com/github/dudeperf3ct/RL_Notebooks/blob/master/TD/TD_CliffWalking.ipynb)|

# Approximate Methods

Approximate Methods : Blog