thinkingparticle/deep_rl_pong_keras
Deep Reinforcement Learning Policy Gradients Method - Pong game - Keras
This guide helps you understand how to teach an AI to play classic video games like Pong using a method called Reinforcement Learning. You'll input game states and train a neural network, ultimately producing an AI player that can compete in the game. It's for anyone with a basic grasp of neural networks interested in learning the fundamental steps of AI game training.
No commits in the last 6 months.
Use this if you want a step-by-step tutorial to grasp the basics of training an AI for simple game play, especially if you're familiar with Keras.
Not ideal if you're looking for a production-ready, perfectly trained game-playing AI or if you're unfamiliar with neural networks and Keras.
Stars
22
Forks
10
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jun 15, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thinkingparticle/deep_rl_pong_keras"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
Talendar/flappy-bird-gym
An OpenAI Gym environment for the Flappy Bird game
Farama-Foundation/ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
chris-chris/pysc2-examples
StarCraft II - pysc2 Deep Reinforcement Learning Examples
aleju/mario-ai
Playing Mario with Deep Reinforcement Learning
gsurma/atari
AI research environment for the Atari 2600 games 🤖.