# spragunr/deep_q_rl

Theano-based implementation of Deep Q-learning

Repository: https://github.com/spragunr/deep_q_rl
Canonical: https://ross.abutalabs.com/products/deep_q_rl
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2017-04-14T01:57:26+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": 4356, "days_push": 3429, "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 1094, forks 341 (observed 2026-08-28T04:03:33.803064+00:00)

## What it is
A Theano/Lasagne-based implementation of the Deep Q-Network (DQN) algorithm from DeepMind's Atari reinforcement learning papers. It trains neural network agents to play Atari games via the Arcade Learning Environment.

## Use cases
- reproduce the DQN Atari results from the NIPS 2013 and Nature 2015 papers
- train a deep Q-learning agent to play Atari games
- study an educational reference implementation of deep reinforcement learning
- experiment with deep Q-learning hyperparameters on classic RL benchmarks

## When to choose
- you want to reproduce or study the original DQN papers' results
- you need a simple, readable reference implementation of deep Q-learning
- you are doing research or coursework on deep reinforcement learning with legacy Theano tooling

## When to avoid
- you need a maintained framework for modern RL research (use stable-baselines3, RLlib, or CleanRL)
- your project runs on modern PyTorch/TensorFlow stacks
- you need Windows or CPU-only training support
- you cannot invest days of GPU training time

## Facets
- artifact type: library
- maturity: abandoned
- function: reinforcement-learning, deep-learning, machine-learning
- domain: reinforcement-learning, machine-learning, deep-learning, gaming-tools
- platform: python
- tags: deep-q-learning, theano, lasagne, atari, dqn, arcade-learning-environment, linux, gpu

## Member repositories
- spragunr/deep_q_rl (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.803064+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 2026-08-30T06:47:38.392688+00:00, confidence not recorded.
  - readme: https://github.com/spragunr/deep_q_rl (fetched 2026-08-28T04:03:33.803064+00:00, sha ad48c1a93489)
- Data as of 2026-08-30T08:39:29.467469+00:00.