CS229 Final Report Deep Q-Learning to Play Mario

نویسنده

  • Sean Klein
چکیده

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.

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 Reinforcement Learning to Play Mario

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 f...

متن کامل

CS229 Project Final Report Deep Q-Learning on Arcade Game Assault

Atari 2600 Assault is a game environment provided on the OpenAI Gym platform; it is a top-down shoot’em up game where the player gains reward points for destroying enemy ships. The enemy consists of a mothership and smaller vessels that shoot at the player. The player can move and shoot in various directions with a total of 7 actions available. Every time the player shoots, a heat meter keeps t...

متن کامل

Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening

We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the training time. We evaluate the performance of our approach on the 49 games of the ch...

متن کامل

An Information-Theoretic Optimality Principle for Deep Reinforcement Learning

We methodologically address the problem of Qvalue overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates. The resultant algorithm encompasses a wide range of learning outcomes containing deep Q-networks as a special case. Differ...

متن کامل

Deep Attention Recurrent Q-Network

A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind’s team called the approach: Deep Q-Network (DQN). We present an extension of DQN by “soft” and “hard” attention mechanisms. Tests of the proposed Deep Attention Recurrent Q-Network (DAR...

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 2016