# quantumiracle/Popular-RL-Algorithms

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

Repository: https://github.com/quantumiracle/Popular-RL-Algorithms
Canonical: https://ross.abutalabs.com/products/popular-rl-algorithms
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: reinforcement-learning, soft-actor-critic, state-of-the-art
Last push: 2025-03-13T20:22:24+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 11, release rhythm 35, longevity 100
- inputs: {"age_days": 2693, "days_push": 538, "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 1358, forks 147 (observed 2026-08-28T04:04:29.689196+00:00)

## What it is
A personal collection of PyTorch implementations of popular model-free reinforcement learning algorithms (SAC, TD3, PPO, DDPG, Q-learning, QMIX, and more) tested on OpenAI Gym and a custom Reacher environment. It is a study/research reference rather than a packaged library, with multiple implementation variants shown for comparison.

## Use cases
- learn how SAC is implemented in PyTorch
- compare multiple implementations of the same RL algorithm
- study PPO or TD3 source code for a course
- find reference code for model-free RL algorithms
- get a starting point for implementing a custom RL algorithm
- understand differences between SAC versions

## When to choose
- you want readable, educational implementations of classic RL algorithms
- you want to see multiple variants of an algorithm side by side
- you are studying reinforcement learning and want reference code rather than a black-box library

## When to avoid
- you need a production-ready or well-structured RL library
- you want a stable high-level API for training RL agents
- you need maintained, tested code with clean abstractions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, reinforcement-learning
- domain: reinforcement-learning, machine-learning, tutorials
- platform: python
- tags: pytorch, model-free-rl, openai-gym, sac, td3, ppo, research-code, jupyter-notebook

## Member repositories
- quantumiracle/Popular-RL-Algorithms (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.689196+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 2026-08-30T04:41:46.898266+00:00, confidence not recorded.
  - readme: https://github.com/quantumiracle/Popular-RL-Algorithms (fetched 2026-08-28T04:04:29.689196+00:00, sha 74da5197795f)
- Data as of 2026-08-30T08:39:29.467469+00:00.