carpedm20/deep-rl-tensorflow

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1580 stars · 394 forks observed · 2026-08-28

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

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

library · maturity abandoned

reinforcement-learning machine-learning deep-learning reinforcement-learning machine-learning deep-learning python dqn atari openai-gym tensorflow research-code

Member repositories

For agents

markdown · JSON · MCP: product_card(name="carpedm20/deep-rl-tensorflow")