# seungeunrho/minimalRL

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

Repository: https://github.com/seungeunrho/minimalRL
Canonical: https://ross.abutalabs.com/products/minimalrl
Language: Python
License: MIT
License Family: permissive
Topics: deep-reinforcement-learning, pytorch, simple, deep-learning, a3c, ppo, a2c, reinforce, acer, dqn, ddpg, policy-gradients, reinforcement-learning, machine-learning, sac
Last push: 2023-04-22T09:06:41+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": 2689, "days_push": 1229, "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 3222, forks 491 (observed 2026-08-28T04:07:49.786006+00:00)

## What it is
A collection of minimal PyTorch implementations of classic deep reinforcement learning algorithms (REINFORCE, DQN, PPO, DDPG, A3C, A2C, ACER, SAC, and more), each fitting in a single 100-150 line file. It is designed for learning, with every algorithm trainable on CartPole-v1 in under 30 seconds without a GPU.

## Use cases
- learn reinforcement learning algorithms from short readable code
- understand how DQN or PPO works by reading a single file
- quickly train basic RL agents on CartPole without a GPU
- study PyTorch implementations of policy gradient methods
- get a minimal reference implementation of SAC or DDPG
- teach a deep RL course with simple code examples

## When to choose
- you want to learn or teach RL algorithm internals with minimal code
- you need compact reference implementations to read or modify
- you want fast, CPU-friendly experiments on simple environments

## When to avoid
- you need production-ready, scalable, or feature-rich RL training
- you need complex environments beyond CartPole-v1
- you need a maintained framework with active development and support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning, education, tutorials
- platform: python, cross-platform
- tags: pytorch, reinforcement-learning-algorithms, educational, minimal-implementations, cartpole, openai-gym, policy-gradients, dqn, ppo, sac, a3c

## Member repositories
- seungeunrho/minimalRL (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.786006+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 2026-08-29T18:44:19.907408+00:00, confidence not recorded.
  - readme: https://github.com/seungeunrho/minimalRL (fetched 2026-08-28T04:07:49.786006+00:00, sha db704bb7d5c3)
- Data as of 2026-08-30T08:39:29.467469+00:00.