DTS307TC Reinforcement Learning

Coursework - Individual Lab Report

Due:  23:59, Friday, May 9, 2025

Weight: 40%

Maximum score: 40 marks

Overview

The purpose of this assignment is to gain experience in Python programming and the design of reinforcement leaning algorithms.  You are expected to implement an RL algorithm that solves a specific environment and provide an explanation of the algorithm’s methodology. You are expected to analyse your results, including challenges and your solutions.

Learning Outcomes Assessed

A: Systematically understand the fundamental concepts and principles of reinforcement learning

B: Critically analyse real-life problem situations and expertly map them as reinforcement learning tasks.

C: Mastery of Monte Carlo Methods and Temporal Difference Learning

D: Proficiency in Deep Reinforcement Learning algorithms

Late policy

5% of the total marks available for the assessment shall be deducted from the assessment mark for each working day after the submission date, up to a maximum of five working days

Avoid Plagiarism

• Do not submit work from other students.

• Do not share code/work with other students

• Do not use open-source code as it is or without proper reference.

Risks

• Please read the coursework instructions and requirements carefully. Not following these instructions and requirements may result in a loss of marks.

• The assignment must be submitted via Learning Mall. Only electronic submission is accepted and no hard copy submission.

• All students must download their file and check that it is viewable after submission. Documents may become corrupted during the uploading process (e.g.  due to slow internet connections). However, students are responsible for submitting a functional and correct file for assessments.

• Academic Integrity Policy is strictly followed.

Lab Report (40 marks)

The lab reports must include two labs (lab3 and lab4), incorporating your source code, analysis, and supporting evidence.  Ensure that screenshots of the outputs and activities are included.  Detailed instructions for each lab can be found in the respective lab manuals, and it is crucial that your report strictly follows these guidelines:

• Do NOT use Stable-baselines libraries or any other reinforcement learning specific libraries in your code.

• Do NOT exceed the word count limit of 3000 words for each report, reference and appendix excluded.

• Although you are allowed to use any generative AI tools to assist your work, please keep in mind

that you should be using them responsibly.  (Good use: Improve your report after writing it and always review its output to ensure that it is correct. Bad use: Copy-pasting an entire report from AI without any effort of your own. )

The distribution of marks is as follows:

• The report for Lab3: A2C [20 marks]

• The report for Lab4: PPO [20 marks]

Submission Requirements

Please prepare and submit the following documents:

• A cover page featuring your student ID.

• A zip file containing all the source codes, which should be named using your full name and student ID in the following format: CW1_Name_ID.zip

• Two PDF files that include all your responses for the 2 labs, your reports, and documentation

of your lab work.  The files should be named in the following format:  CW1_Lab3_ID.pdf and CW1_Lab4_ID.pdf

Note that the quality of the code, the clarity of your writing, and the format/style. of your report will be taken into consideration during the evaluation. The detailed rubric is outlined below.

Rubric