Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
7-2018
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.
Keywords
Deep reinforcement learning, Snake Game, autonomous agent, experience replay
Discipline
Databases and Information Systems | Software Engineering
Research Areas
Data Science and Engineering
Publication
Proceedings of 2018 IEEE International Conference on Agents (ICA), Singapore, July 28-31
First Page
1
Last Page
6
ISBN
9781538681817
Identifier
10.1109/AGENTS.2018.8460004
Publisher
IEEE
City or Country
New York
Citation
1
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.