https://github.com/wielkadraka/ai_pacman_a3c

AI playing Packman. This AI model is based on A3C (Asynchronous Advantage Actor Critic) algoritm
https://github.com/wielkadraka/ai_pacman_a3c

a3c ai python3 pytorch

Last synced: about 2 months ago
JSON representation

AI playing Packman. This AI model is based on A3C (Asynchronous Advantage Actor Critic) algoritm

• Host: GitHub
• URL: https://github.com/wielkadraka/ai_pacman_a3c
• Owner: WielkaDraka
• License: mit
• Created: 2024-07-20T13:10:32.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-21T15:43:29.000Z (6 months ago)
• Last Synced: 2024-07-21T17:18:28.086Z (6 months ago)
• Topics: a3c, ai, python3, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 9.77 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AI play Pacman game

## Asynchronous Advantage Actor-Critic (A3C)

Asynchronous Advantage Actor-Critic (A3C) is a reinforcement learning algorithm that uses multiple agents to interact with the environment in parallel, improving training efficiency and stability.

### Key Features:

- **Asynchronous Learning:** Multiple agents explore the environment simultaneously, reducing correlation.

- **Actor-Critic Method:** The actor learns the policy, while the critic estimates the value function.

### Applications:

- Complex game environments (e.g., Doom, StarCraft)

- Robotics

- Real-time strategy games