The full list of requirements is in requirements.txt. If you encounter any error with torch=1.7.1, you might need to install Visual C++ 2015-2019 (or simply downgrade your pytorch version, it should be fine). This project requires Python 3.6 with the pygame library installed, as well as Pytorch.
Osx screen snake how to#
We are going to see how a Deep Q-Learning algorithm learns how to play Snake, scoring up to 50 points and showing a solid strategy after only 5 minutes of training.Īdditionally, it is possible to run the Bayesian Optimization method to find the optimal parameters of the Deep neural network, as well as some parameters of the Deep RL approach. The goal for the system is to figure it out and elaborate a strategy to maximize the score - or the reward. This version includes multiplayer games, highscores, levels, and various little additions that should make the gameplay comfort. But instead of moving the snake in a window, the snake moves across your screen itself, or even from screen to screen. No rules about the game are given, and initially the Bot has no information on what it needs to do. Screen Snake is a re-make of the classic snake game. This approach consists in giving the system parameters related to its state, and a positive or negative reward based on its actions. In order to do it, I implemented a Deep Reinforcement Learning algorithm. The goal of this project is to develop an AI Bot able to learn how to play the popular game Snake from scratch. Download Snake On Phone Screen- Hissing Snake 1.0 Apk free. To see the old version of the code in Keras/TF, please refer to this repository: snake-ga-tf. The code of Deep Reinforcement Learning was ported from Keras/TF to Pytorch.It is now possible to optimize the Deep RL approach using Bayesian Optimization.This project has been recently updated and improved: Deep Reinforcement Learning Project: Train AI to play Snake