devsisters/DQN-tensorflow

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2583 stars · 756 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow implementation of the Deep Q-Network (DQN) algorithm from the DeepMind paper 'Human-Level Control through Deep Reinforcement Learning'. It trains agents to play Atari games via OpenAI Gym, including experience replay and fixed Q-target networks.

Use cases

• train a DQN agent to play Atari games like Breakout
• learn how deep Q-learning and experience replay are implemented
• reproduce results from the DeepMind DQN paper
• experiment with DQN variants like Double and Dueling DQN
• benchmark reinforcement learning training on a GPU

When to choose

• you want a readable reference implementation of the original DQN paper
• you are studying or teaching deep reinforcement learning with classic TensorFlow
• you need a baseline for comparing DQN variants on Atari environments

When to avoid

• you need modern, maintained RL libraries - it depends on TensorFlow 0.12 and Python 2.7-era tooling
• you want production RL training at scale
• you need PyTorch or current TensorFlow 2.x compatibility

Facets

library · maturity abandoned

machine-learning reinforcement-learning deep-learning reinforcement-learning machine-learning deep-learning gaming-tools python dqn tensorflow openai-gym atari q-learning experience-replay research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="devsisters/DQN-tensorflow")