# siemanko/tensorflow-deepq

A deep Q learning demonstration using Google Tensorflow

Repository: https://github.com/siemanko/tensorflow-deepq
Canonical: https://ross.abutalabs.com/products/tensorflow-deepq
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2017-05-24T22:11:09+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": 3946, "days_push": 3388, "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 1166, forks 289 (observed 2026-08-28T04:03:50.307353+00:00)

## What it is
A Jupyter Notebook-based demonstration of deep Q-learning implemented with TensorFlow, including controllers and simulators that can be combined to train agents in simple game environments. The repository is explicitly marked obsolete in favor of OpenAI Baselines.

## Use cases
- learn how deep Q-learning works
- see a reinforcement learning demo in tensorflow
- build a simple RL agent for a toy game
- understand controller and simulator design in RL
- experiment with deep Q networks in notebooks

## When to choose
- you want an educational, readable deep Q-learning example
- you are studying older TensorFlow 1.x RL code
- you want a minimal framework to hack on controllers and simulations

## When to avoid
- you need a maintained or production-ready RL library
- you want modern TensorFlow or PyTorch support
- you need state-of-the-art RL algorithms - use OpenAI Baselines or Stable Baselines instead

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: reinforcement-learning, machine-learning, simulation
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: deep-q-learning, tensorflow, jupyter-notebook, demonstration, obsolete

## Member repositories
- siemanko/tensorflow-deepq (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:50.307353+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 2026-08-30T06:29:18.387650+00:00, confidence not recorded.
  - readme: https://github.com/siemanko/tensorflow-deepq (fetched 2026-08-28T04:03:50.307353+00:00, sha 941fbac6ca82)
- Data as of 2026-08-30T08:39:29.467469+00:00.