# nikitasrivatsan/DeepLearningVideoGames

Repository: https://github.com/nikitasrivatsan/DeepLearningVideoGames
Canonical: https://ross.abutalabs.com/products/deeplearningvideogames
Language: Python
License Family: other
Last push: 2023-05-04T07:19:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3957, "days_push": 1217, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1090, forks 216 (observed 2026-08-28T04:03:32.801317+00:00)

## What it is
A research project implementing Deep Q Networks (DQN) to learn video game strategies for Pong and Tetris from raw pixel input. It uses a convolutional neural network trained with Q learning to approximate expected rewards and select optimal actions.

## Use cases
- learn to play pong with deep reinforcement learning
- train a dqn on atari games from pixels
- example of q learning with convolutional neural networks
- study deep q network implementation in python
- reproduce deepmind atari results
- learn reinforcement learning for video games

## When to choose
- learning how DQN works with a small readable codebase
- reproducing classic deep RL paper results on Pong or Tetris
- teaching or studying deep reinforcement learning from pixels

## When to avoid
- production reinforcement learning systems
- modern high-performance RL training with maintained libraries
- projects requiring support or recent updates

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, reinforcement-learning, machine-learning, image-processing
- domain: reinforcement-learning, deep-learning, machine-learning, gaming-tools
- platform: python
- tags: deep-q-networks, q-learning, atari, pong, tetris, convolutional-neural-networks, research-project

## Member repositories
- nikitasrivatsan/DeepLearningVideoGames (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.801317+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 2026-08-30T06:49:13.852566+00:00, confidence not recorded.
  - readme: https://github.com/nikitasrivatsan/DeepLearningVideoGames (fetched 2026-08-28T04:03:32.801317+00:00, sha 124f52a3f27e)
- Data as of 2026-08-30T08:39:29.467469+00:00.