Searching Algorithms with Q-learning for Snake game

2021 COE Engineering Design Project (TY05)

---

Faculty Lab Coordinator

Truman Yang

Topic Category

Software Systems

Preamble

In games, AI is the reason behind of programming an opposition player who calls it as the Non-player characters (NPC). To move an NPC’s from one place to another place, searching algorithms are required. Since searching algorithm in a game takes a lot of time, the best searching algorithm is to be implemented in the game to get efficient results. In this project, different AI searching algorithms will be implemented and evaluated in a snake game. Q-learning will be combined with search algorithms to further improve their performance.

Objective

In this project, students need to implement a few searching algorithms for a snake game. The performance of different searching algorithms will be compared in terms of the score achieved by each algorithm. In addition, learning ability with Q-learning should be added to search algorithms. The effectiveness of these solutions will also be evaluated.

Partial Specifications

(1) Your design will be based on existing code of searching and Q-learning algorithms. Further improvement on design and performance evaluation are needed.
(2) Software development with Python should be efficient and effective.

Suggested Approach

(1) Literature review of Q-learning on games will be conducted.
(2) Familiar with related projects with reading, implementation and evaluation
(3) Idea generation technique with SCAMPER.

Group Responsibilities

Design, implement, and test the algorithms as specified above.

Student A Responsibilities

Implement and evaluate searching algorithms for snake game

Student B Responsibilities

Implement and evaluate Q-learning algorithm on the snake game

Student C Responsibilities

Design Q-learning based searching algorithms

Student D Responsibilities

Implement and evaluate Q-learning based searching algorithms

Course Co-requisites

AI-related courses COE318: Software Systems

To ALL EDP Students

Due to COVID-19 pandemic, in the event University is not open for in-class/in-lab activities during the Winter term, your EDP topic specifications, requirements, implementations, and assessment methods will be adjusted by your FLCs at their discretion.