https://github.com/wielkadraka/lunar-landing-q-learing

AI playing Lunar Landing from python gymnasium library
https://github.com/wielkadraka/lunar-landing-q-learing

deep-neural-networks deep-q-learning lunar-lander python3

Last synced: about 2 months ago
JSON representation

AI playing Lunar Landing from python gymnasium library

• Host: GitHub
• URL: https://github.com/wielkadraka/lunar-landing-q-learing
• Owner: WielkaDraka
• Created: 2024-07-21T17:31:01.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-21T17:36:00.000Z (6 months ago)
• Last Synced: 2024-07-21T19:25:36.456Z (6 months ago)
• Topics: deep-neural-networks, deep-q-learning, lunar-lander, python3
• Language: Jupyter Notebook
• Homepage:
• Size: 8.79 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Lunar-Landing-Q-Learing

AI playing Lunar Landing from python gymnasium library

Deep Q-Learning (DQN) is an extension of Q-learning, a model-free reinforcement learning algorithm. It uses a deep neural network to approximate the Q-value function, which represents the expected future rewards for an agent's actions in a given state.

### Key Features:

- **Experience Replay:** Stores past experiences to break correlation between consecutive samples and stabilize training.

- **Target Network:** Uses a separate network to calculate target Q-values to improve stability.

### Applications:

- Game playing (e.g., Atari games)

- Robotic control

- Navigation tasks