# carpedm20/deep-rl-tensorflow

TensorFlow implementation of Deep Reinforcement Learning papers

Repository: https://github.com/carpedm20/deep-rl-tensorflow
Canonical: https://ross.abutalabs.com/products/deep-rl-tensorflow
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, deep-reinforcement-learning, dqn
Last push: 2018-06-04T07:19:33+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": 3736, "days_push": 3012, "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 1580, forks 394 (observed 2026-08-28T04:05:06.906017+00:00)

## What it is
A TensorFlow implementation of several Deep Reinforcement Learning papers, including DQN, Double DQN, and Dueling networks, for training agents on OpenAI Gym environments like Atari games. It is a research/reference codebase written in Python 2.7 with TensorFlow 0.12.

## Use cases
- train a DQN agent on Atari games
- reproduce deep Q-learning paper results
- learn how DQN is implemented in TensorFlow
- compare Double DQN and Dueling DQN variants
- experiment with deep reinforcement learning in OpenAI Gym

## When to choose
- you want readable reference implementations of classic DQN papers
- you are studying deep reinforcement learning algorithms
- you need a starting point to modify DQN variants yourself

## When to avoid
- you need a maintained library with modern TensorFlow or PyTorch support
- you are on Python 3 or recent GPU stacks
- you want production-ready RL training infrastructure

## Facets
- artifact type: library
- maturity: abandoned
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: dqn, atari, openai-gym, tensorflow, research-code

## Member repositories
- carpedm20/deep-rl-tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:06.906017+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 2026-08-30T03:56:36.552938+00:00, confidence not recorded.
  - readme: https://github.com/carpedm20/deep-rl-tensorflow (fetched 2026-08-28T04:05:06.906017+00:00, sha 91fba710409e)
- Data as of 2026-08-30T08:39:29.467469+00:00.