# qfettes/DeepRL-Tutorials

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

Repository: https://github.com/qfettes/DeepRL-Tutorials
Canonical: https://ross.abutalabs.com/products/deeprl-tutorials
Language: Jupyter Notebook
License Family: other
Topics: python3, pytorch, reinforcement-learning, deep-reinforcement-learning, deep-q-network, double-dqn, multi-step-learning, dueling-dqn, noisy-networks, prioritized-experience-replay, deeprl-tutorials, categorical-dqn, rainbow, quantile-regression, deep-recurrent-q-network, actor-critic, advantage-actor-critic, a2c, gae, ppo
Last push: 2021-05-19T23:12:14+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": 3016, "days_push": 1932, "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 1078, forks 326 (observed 2026-08-28T04:03:29.933003+00:00)

## What it is
A collection of IPython/Jupyter notebooks implementing deep reinforcement learning algorithms in PyTorch, covering DQN variants (Double, Dueling, Noisy Nets, Prioritized Replay, Categorical, Rainbow, Quantile Regression, DRQN) and actor-critic methods (A2C, GAE). Each notebook maps to a published paper and prioritizes readability for learning.

## Use cases
- learn deep reinforcement learning algorithms from readable PyTorch implementations
- understand the Rainbow DQN paper by reading annotated code
- study DQN variants like double DQN, dueling DQN, and noisy networks
- find a reference implementation of prioritized experience replay
- learn actor-critic methods like A2C and PPO with GAE
- supplement RL paper reading with working notebook code

## When to choose
- you want readable, educational implementations tied to specific RL papers
- you prefer PyTorch and Jupyter notebooks for studying algorithms
- you are learning distributional RL, Rainbow, or quantile regression DQN

## When to avoid
- you need production-ready, efficient, or maintained RL libraries
- you need a library with a stable API, tests, or license
- you want on-policy algorithms beyond A2C/GAE or the latest RL methods

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, reinforcement-learning, developer-tools
- domain: reinforcement-learning, machine-learning, tutorials, deep-learning
- platform: python, cross-platform
- tags: pytorch, jupyter-notebooks, dqn, rainbow, ppo, a2c, actor-critic, prioritized-experience-replay, educational, gpu

## Member repositories
- qfettes/DeepRL-Tutorials (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.933003+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 2026-08-30T06:53:11.877416+00:00, confidence not recorded.
  - readme: https://github.com/qfettes/DeepRL-Tutorials (fetched 2026-08-28T04:03:29.933003+00:00, sha 67ed7a9f95ed)
- Data as of 2026-08-30T08:39:29.467469+00:00.