# rlcode/reinforcement-learning

Minimal and Clean Reinforcement Learning Examples

Repository: https://github.com/rlcode/reinforcement-learning
Canonical: https://ross.abutalabs.com/products/rlcode-reinforcement-learning
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, deep-learning, deep-reinforcement-learning, machine-learning, policy-gradient, deep-q-network, dqn, actor-critic, a3c
Last push: 2026-06-12T03:36:43+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 100
- inputs: {"age_days": 3519, "days_push": 82, "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 3659, forks 735 (observed 2026-08-28T04:08:13.257080+00:00)

## What it is
A collection of minimal, clean, one-file-per-algorithm reinforcement learning examples in Python, covering classic methods like Q-Learning and SARSA up to deep RL like DQN, PPO, and A3C. It includes benchmark results on Grid World, CartPole, and Atari environments with reproducible training reports.

## Use cases
- learn reinforcement learning from readable code examples
- understand how DQN works with a minimal implementation
- study PPO and actor-critic algorithms in one file
- find reference implementations of Q-learning and SARSA
- compare RL algorithm benchmarks on Atari and CartPole
- get started with deep reinforcement learning in Python

## When to choose
- you want clean, minimal, educational RL implementations rather than a heavy framework
- you are learning RL algorithms and prefer one readable file per algorithm
- you want reproducible benchmark baselines for DQN and PPO on standard environments

## When to avoid
- you need a production-ready RL library with parallel environments and hyperparameter tuning
- you want a framework API to plug algorithms into your own project rather than standalone examples
- you need state-of-the-art performance or extensive multi-seed evaluation

## Facets
- artifact type: learning-resource
- maturity: active
- function: reinforcement-learning, machine-learning, deep-learning, benchmarking
- domain: reinforcement-learning, machine-learning, education, tutorials
- platform: python, cross-platform
- tags: dqn, ppo, actor-critic, policy-gradient, q-learning, sarsa, atari, cartpole, grid-world, pytorch, educational-examples, gpu

## Member repositories
- rlcode/reinforcement-learning (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:13.257080+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 2026-08-29T18:31:36.458528+00:00, confidence not recorded.
  - readme: https://github.com/rlcode/reinforcement-learning (fetched 2026-08-28T04:08:13.257080+00:00, sha 28639711d016)
- Data as of 2026-08-30T08:39:29.467469+00:00.