CS229 Final Report Reinforcement Learning to Play Mario

نویسندگان

  • Yizheng Liao
  • Kun Yi
  • Zhe Yang
چکیده

In this paper, we study applying Reinforcement Learning to design a automatic agent to play the game Super Mario Bros. One of the challenge is how to handle the complex game environment. By abstracting the game environment into a state vector and using Q learning — an algorithm oblivious to transitional probabilities — we achieve tractable computation time and fast convergence. After training for 5000 iterations, our agent is able to win about 90% of the time. We also compare and analyze the choice of different learning rate α and discount factor γ.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

CS229 Final Report Deep Q-Learning to Play Mario

In this paper, I study applying applying and adjusting DeepMind’s Atari Deep Q-Learning model to train an automatic agent to play the 1985 Nintendo game Super Mario Bros. The agent learns control policies from raw pixel data using deep reinforcement learning. The model is a convolutional neural network that trained through only raw frames of the game and basic info such as score and motion.

متن کامل

CS229 Final Project: Language Grounding in Minecraft with Gated-Attention Networks

A key question in language understanding is the problem of language grounding – how do symbols such as words get their meaning? We examine this question in the context of task oriented language grounding in gameplay. In order to perform tasks and challenges specified by natural language instructions, agents need to extract semantically meaningful representations of language and map it to the vi...

متن کامل

An Object-Oriented Approach to Reinforcement Learning in an Action Game

In this work, we look at the challenge of learning in an action game, Infinite Mario. Learning to play an action game can be divided into two distinct but related problems, learning an object-related behavior and selecting a primitive action. We propose a framework that allows for the use of reinforcement learning for both of these problems. We present promising results in some instances of the...

متن کامل

Learning to Play Mario

Computer Games are interesting test beds for research in Artificial Intelligence and Machine Learning. Games usually have continuous state spaces, large action spaces and are characterized by complex relationships between components. Without applying abstraction and generalizations, learning in computer games domain becomes infeasible. Through this work, we investigate some designs that facilit...

متن کامل

COMP3211 Final Project Report Tetris AI Using Reinforcement Learning

Software Running Instruction First, there are two version of the game. One is implemented with learning part and it would play ang learn the game with zero knowledge at the beginning. Another is implemented with our optimised results and evaluation function after the learning process. This version would always play the same strategy. Before running the files, please make sure the corresponding ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012