Using Machine Learning To Play Pacman

Using Machine Learning To Play Pacman

Ashok Kumar

Ashok Kumar

Allahabad, Uttar Pradesh

The aim of this project is to train an agent to achieve high scores on popular Atari Game Pacman using Reinforcement Learning.

Artificial Intelligence

  • 0 Collaborators

  • 1 Followers

    Follow

Description

Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed. Reinforcement learning (RL) is an area of machine learning inspired by behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Reinforcement Learning has been called as the first step towards general artificial intelligence an AI that can survive in a variety of environments, instead of being confined to strict realms such as playing chess. Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think. AI is accomplished by studying how human brain thinks, and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems. The aim of this project is to combine Reinforcement Learning with other Machine Learning techniques like Linear Function Approximation and Neural Networks to train an agent to achieve high scores on popular Atari game Pacman. I experiments with different algorithms, hyperparameters and network architectures leading to better performance of my agent.

Gallery

Video

Medium 13177798 988305177931780 7083426798291791059 n

Ashok K. created project Using Machine Learning To Play Pacman

Medium 4b904ee0 e306 4bcd a509 009913c7526d

Using Machine Learning To Play Pacman

Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed. Reinforcement learning (RL) is an area of machine learning inspired by behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Reinforcement Learning has been called as the first step towards general artificial intelligence an AI that can survive in a variety of environments, instead of being confined to strict realms such as playing chess. Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think. AI is accomplished by studying how human brain thinks, and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems. The aim of this project is to combine Reinforcement Learning with other Machine Learning techniques like Linear Function Approximation and Neural Networks to train an agent to achieve high scores on popular Atari game Pacman. I experiments with different algorithms, hyperparameters and network architectures leading to better performance of my agent.

No users to show at the moment.