AdamStelmaszczyk/dqn

TensorFlow & Keras implementation of DQN with HER (Hindsight Experience Replay)

33
/ 100
Emerging

This project helps machine learning researchers and reinforcement learning practitioners train AI agents to play Atari games using Deep Q-Networks (DQN) with Hindsight Experience Replay (HER). It takes game state observations as input and outputs a trained model capable of making decisions within the game environment. The primary users are researchers exploring deep reinforcement learning algorithms and AI game agents.

No commits in the last 6 months.

Use this if you are a researcher or student looking to experiment with or replicate Deep Q-Networks with Hindsight Experience Replay for Atari game environments.

Not ideal if you need a plug-and-play solution for general AI game playing or if your focus is on domains outside of Atari game environments.

reinforcement-learning-research atari-game-ai deep-q-networks machine-learning-experimentation ai-agent-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

40

Forks

4

Language

Python

License

GPL-3.0

Last pushed

Jul 31, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AdamStelmaszczyk/dqn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.