A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents

TL;DR

This paper introduces a memory-efficient deep reinforcement learning approach for the Snake game, utilizing a lightweight CNN and simplified mechanisms to reduce resource usage while maintaining competitive performance.

Contribution

It proposes a novel, resource-conscious DRL method that operates effectively with compressed data and minimal environment information, suitable for devices with limited resources.

Findings

Achieves comparable performance to existing DRL methods

Uses less memory and computational time

Operates effectively with compressed imagery data

Abstract

To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more important for many applications and devices to reduce memory usage and computational times than to achieve the maximum reward. This paper presents a modified DRL method that performs reasonably well with compressed imagery data without requiring additional environment information and also uses less memory and time. We have designed a lightweight Convolutional Neural Network (CNN) with a variant of the Q-network that efficiently takes preprocessed image data as input and uses less memory. Furthermore, we use a simple reward mechanism and small experience replay memory so as to provide only the minimum necessary information. Our modified DRL method enables our autonomous agent to play Snake, a classical control game. The results show our model can achieve similar performance as other DRL methods.