# yenchenlin/DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

Repository: https://github.com/yenchenlin/DeepLearningFlappyBird
Canonical: https://ross.abutalabs.com/products/deeplearningflappybird
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, deep-reinforcement-learning, game
Last push: 2024-08-07T16:58:16+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": 3823, "days_push": 756, "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 6818, forks 2058 (observed 2026-08-28T04:09:48.808977+00:00)

## What it is
A Python demo that trains a Deep Q-Network (DQN) to play Flappy Bird from raw pixel input using TensorFlow, pygame, and OpenCV. It serves as an educational reference implementation of the Deep Q-Learning algorithm from the Atari DQN paper.

## Use cases
- learn deep reinforcement learning with a hands-on example
- see how DQN plays Flappy Bird from raw pixels
- reference implementation of Deep Q-Network algorithm
- teaching demo for Q-learning with convolutional networks
- starting point for game-playing RL experiments

## When to choose
- you want a small, readable DQN example to study
- you are teaching or learning deep reinforcement learning basics
- you want to see pixel-based RL applied to a simple game

## When to avoid
- you need a production or maintained RL framework
- you need modern TensorFlow versions or up-to-date dependencies
- you need scalable or multi-environment RL training

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, reinforcement-learning, machine-learning, game
- domain: deep-learning, reinforcement-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: dqn, deep-q-network, flappy-bird, tensorflow, pygame, demo, educational, game-development

## Member repositories
- yenchenlin/DeepLearningFlappyBird (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.808977+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 2026-08-29T17:41:55.702885+00:00, confidence not recorded.
  - readme: https://github.com/yenchenlin/DeepLearningFlappyBird (fetched 2026-08-28T04:09:48.808977+00:00, sha 202e5c9ede25)
- Data as of 2026-08-30T08:39:29.467469+00:00.