Autonomous agents in snake game via deep reinforcement learning
Author
Wei, Zhepei
Wang, Di
Zhang, Ming
Tan, Ah-Hwee
Miao, Chunyan
Zhou, You
Date of Issue
2018Conference Name
2018 IEEE International Conference on Agents (ICA)
School
School of Computer Science and Engineering
Version
Accepted version
Abstract
Since DeepMind pioneered a deep reinforcement learning (DRL) model to play the Atari games, DRL has become a commonly adopted method to enable the agents to learn complex control policies in various video games. However, similar approaches may still need to be improved when applied to more challenging scenarios, where reward signals are sparse and delayed. In this paper, we develop a refined DRL model to enable our autonomous agent to play the classical Snake Game, whose constraint gets stricter as the game progresses. Specifically, we employ a convolutional neural network (CNN) trained with a variant of Q-learning. Moreover, we propose a carefully designed reward mechanism to properly train the network, adopt a training gap strategy to temporarily bypass training after the location of the target changes, and introduce a dual experience replay method to categorize different experiences for better training efficacy. The experimental results show that our agent outperforms the baseline model and surpasses human-level performance in terms of playing the Snake Game.
Subject
Deep Reinforcement Learning
Snake Game
Engineering::Computer science and engineering
Snake Game
Engineering::Computer science and engineering
Type
Conference Paper
Rights
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/AGENTS.2018.8460004
Collections
https://doi.org/10.1109/AGENTS.2018.8460004
Get published version (via Digital Object Identifier)