# mimoralea/gdrl

Grokking Deep Reinforcement Learning

Repository: https://github.com/mimoralea/gdrl
Canonical: https://ross.abutalabs.com/products/gdrl
Homepage: https://www.manning.com/books/grokking-deep-reinforcement-learning
Language: Jupyter Notebook
License: BSD-3-Clause
License Family: permissive
Topics: deep-learning, deep-reinforcement-learning, reinforcement-learning, machine-learning, algorithms, artificial-intelligence, neural-networks, pytorch, pytorch-tutorials, numpy, numpy-tutorial, docker, gpu, nvidia-docker
Last push: 2022-02-04T21:19:47+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": 3094, "days_push": 1671, "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 1036, forks 278 (observed 2026-08-28T04:03:19.254834+00:00)

## What it is
Companion code repository for the Manning book 'Grokking Deep Reinforcement Learning' by Miguel Morales, containing Jupyter notebooks covering deep RL from mathematical foundations to advanced actor-critic methods. The code is designed to run in a preconfigured Docker container with optional NVIDIA GPU support.

## Use cases
- learn deep reinforcement learning from scratch
- study DQN and value-based deep RL methods
- understand policy-gradient and actor-critic algorithms
- run RL notebook examples in a reproducible Docker environment
- get hands-on PyTorch and NumPy practice for RL agents
- follow along with the Grokking Deep Reinforcement Learning book exercises

## When to choose
- you want a structured, book-guided path into deep reinforcement learning
- you prefer runnable Jupyter notebooks over reading theory alone
- you want a preconfigured Docker environment so setup just works
- you are learning value-based and actor-critic methods with PyTorch

## When to avoid
- you need a production RL training framework or library
- you want actively updated code for the latest RL algorithms
- you cannot or prefer not to use Docker
- you need a lightweight pip-installable package rather than a notebook collection

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, reinforcement-learning, machine-learning
- domain: reinforcement-learning, deep-learning, machine-learning, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, pytorch, numpy, book-companion-code, nvidia-docker, dqn, policy-gradient, actor-critic, docker, gpu

## Member repositories
- mimoralea/gdrl (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.254834+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 2026-08-30T07:04:42.037878+00:00, confidence not recorded.
  - readme: https://github.com/mimoralea/gdrl (fetched 2026-08-28T04:03:19.254834+00:00, sha ae6fe35d0981)
  - homepage: https://www.manning.com/books/grokking-deep-reinforcement-learning (fetched 2026-08-29T13:05:47.747378+00:00, sha e5e5deaa61d8)
  - site_page: https://www.manning.com/faq (fetched 2026-08-29T13:05:47.756861+00:00, sha 9e27304d7757)
- Data as of 2026-08-30T08:39:29.467469+00:00.