# higgsfield/RL-Adventure

Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL

Repository: https://github.com/higgsfield/RL-Adventure
Canonical: https://ross.abutalabs.com/products/rl-adventure
Language: Jupyter Notebook
License Family: other
Last push: 2021-11-04T22:48:30+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": 3084, "days_push": 1763, "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 3179, forks 590 (observed 2026-08-28T04:07:47.740036+00:00)

## What it is
A step-by-step PyTorch tutorial series implementing Deep Q-Network variants, from vanilla DQN through Double DQN, Prioritized Replay, Noisy Networks, Distributional values, Rainbow, and Hierarchical RL. Each algorithm is presented as a clean, readable Jupyter notebook with links to the original papers.

## Use cases
- learn deep q-learning from scratch with pytorch
- understand rainbow dqn improvements step by step
- implement prioritized experience replay in pytorch
- train a dqn agent on atari pong
- study distributional reinforcement learning with code
- find a readable dqn tutorial with notebooks

## When to choose
- you want to learn DQN and its extensions with clean, minimal PyTorch code
- you prefer notebook-based tutorials tied to original papers
- you want to experiment quickly on CartPole or Atari Pong

## When to avoid
- you need a production-ready or maintained RL library
- you need algorithms beyond DQN-family methods like PPO or SAC
- you require a licensed project for commercial use

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, tutorials, deep-learning
- platform: python
- tags: pytorch, dqn, rainbow, atari, jupyter-notebooks, tutorial, q-learning, gpu

## Member repositories
- higgsfield/RL-Adventure (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.740036+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 2026-08-30T07:25:06.355078+00:00, confidence not recorded.
  - readme: https://github.com/higgsfield/RL-Adventure (fetched 2026-08-28T04:07:47.740036+00:00, sha 121b549bb037)
- Data as of 2026-08-30T08:39:29.467469+00:00.