# vietnh1009/Super-mario-bros-A3C-pytorch

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

Repository: https://github.com/vietnh1009/Super-mario-bros-A3C-pytorch
Canonical: https://ross.abutalabs.com/products/super-mario-bros-a3c-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, a3c, pytorch, gym, python, deep-learning, super-mario-bros, mario, ai
Last push: 2024-04-28T17:37:59+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": 2653, "days_push": 857, "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 1112, forks 237 (observed 2026-08-28T04:03:37.948271+00:00)

## What it is
A clean PyTorch implementation of the Asynchronous Advantage Actor-Critic (A3C) algorithm that trains an agent to play Super Mario Bros via OpenAI Gym. It is written as a simplified, readable reference implementation that follows the original DeepMind paper closely.

## Use cases
- learn how the A3C reinforcement learning algorithm works
- train an AI agent to play Super Mario Bros
- study a minimal PyTorch actor-critic implementation
- reproduce results from the Asynchronous Methods for Deep Reinforcement Learning paper
- get a starting codebase for my own RL game experiments
- compare a clean A3C implementation against more complicated repos

## When to choose
- you want a simple, readable A3C reference implementation in PyTorch
- you are learning reinforcement learning and want minimal setup code
- you want to train an agent on a classic NES game environment

## When to avoid
- you need a production-grade or actively maintained RL framework
- you need distributed or highly optimized training at scale
- you want support for many environments beyond Super Mario Bros out of the box

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, deep-learning, machine-learning
- domain: reinforcement-learning, artificial-intelligence
- platform: python, cross-platform
- tags: a3c, pytorch, gym, super-mario-bros, actor-critic, educational, game-development

## Member repositories
- vietnh1009/Super-mario-bros-A3C-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.948271+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 2026-08-30T06:42:53.598164+00:00, confidence not recorded.
  - readme: https://github.com/vietnh1009/Super-mario-bros-A3C-pytorch (fetched 2026-08-28T04:03:37.948271+00:00, sha 3b43ad2571fa)
- Data as of 2026-08-30T08:39:29.467469+00:00.