# vmayoral/basic_reinforcement_learning

An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.

Repository: https://github.com/vmayoral/basic_reinforcement_learning
Canonical: https://ross.abutalabs.com/products/basic_reinforcement_learning
Language: Jupyter Notebook
License: GPL-3.0
License Family: copyleft
Topics: reinforcement-learning, openai-gym, tutorial, deeplearning, neural-networks, deep-learning, artificial-intelligence, q-learning, ai
Last push: 2023-07-14T07:49:28+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3769, "days_push": 1146, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1224, forks 368 (observed 2026-08-28T04:04:02.815291+00:00)

## What it is
An introductory tutorial series on reinforcement learning with step-by-step Jupyter Notebook walkthroughs covering Q-learning, SARSA, DQN, DDPG, and policy gradient methods. Includes exercises with OpenAI Gym and robotics simulation using ROS and Gazebo.

## Use cases
- learn reinforcement learning from scratch
- understand q-learning with code examples
- implement deep q-networks tutorial
- get started with openai gym
- learn ddpg and policy gradient methods
- apply reinforcement learning to robotics with ros and gazebo
- find beginner reinforcement learning tutorials

## When to choose
- you are new to reinforcement learning and want guided, incremental tutorials
- you prefer learning by coding algorithms from scratch in notebooks
- you want coverage from tabular methods (Q-learning, SARSA) through deep RL (DQN, DDPG, policy gradients)
- you want to combine RL with robotics simulation via ROS and Gazebo

## When to avoid
- you need a production-ready RL library or framework rather than educational code
- you need state-of-the-art algorithms like PPO, SAC, or model-based RL
- you need actively maintained content - several tutorials are unfinished or abandoned
- you need scalable, performant training infrastructure

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning, simulation, benchmarking
- domain: reinforcement-learning, machine-learning, artificial-intelligence, tutorials, robotics
- platform: python, cross-platform
- tags: q-learning, sarsa, dqn, ddpg, policy-gradient, openai-gym, jupyter-notebooks, ros, gazebo, step-by-step-tutorials

## Member repositories
- vmayoral/basic_reinforcement_learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.815291+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 2026-08-30T06:15:30.115139+00:00, confidence not recorded.
  - readme: https://github.com/vmayoral/basic_reinforcement_learning (fetched 2026-08-28T04:04:02.815291+00:00, sha 735604a97127)
- Data as of 2026-08-30T08:39:29.467469+00:00.