# Pulkit-Khandelwal/Reinforcement-Learning-Notebooks

A collection of Reinforcement Learning algorithms from Sutton and Barto's book and other research papers implemented in Python.

Repository: https://github.com/Pulkit-Khandelwal/Reinforcement-Learning-Notebooks
Canonical: https://ross.abutalabs.com/products/reinforcement-learning-notebooks
Language: Jupyter Notebook
License Family: other
Last push: 2018-06-21T20:41:50+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3014, "days_push": 2995, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1045, forks 195 (observed 2026-08-28T04:03:21.525703+00:00)

## What it is
A collection of Jupyter Notebook implementations of reinforcement learning algorithms from Sutton and Barto's book and related research papers, written in Python. It was created as study notes for a graduate RL course at McGill and is intended to accompany the book and David Silver's lecture videos.

## Use cases
- learn reinforcement learning algorithms by reading runnable implementations
- study Sutton and Barto's book with companion code
- implement classic RL algorithms like Q-learning and policy gradients from papers
- supplement David Silver's RL course videos with hands-on notebooks
- reference implementations while taking a reinforcement learning course

## When to choose
- you are learning RL from Sutton and Barto's book and want code to follow along
- you want simple, readable notebook-style implementations of classic RL algorithms
- you are taking a course on reinforcement learning and need study references

## When to avoid
- you need production-ready or well-engineered RL code
- you want a maintained library with an API, tests, or recent updates
- you need modern deep RL frameworks like stable-baselines or RLlib

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: reinforcement-learning, machine-learning, developer-tools
- domain: reinforcement-learning, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: jupyter-notebooks, sutton-barto, educational, algorithms, study-notes

## Member repositories
- Pulkit-Khandelwal/Reinforcement-Learning-Notebooks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.525703+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:02.220888+00:00, confidence not recorded.
  - readme: https://github.com/Pulkit-Khandelwal/Reinforcement-Learning-Notebooks (fetched 2026-08-28T04:03:21.525703+00:00, sha 8f66651f1103)
- Data as of 2026-08-30T08:39:29.467469+00:00.