COMP532-202324 Assignment 2
You need to solve each of the following problems. The assignment aims to design and
implement a deep reinforcement learning agent for a video game from OpenAI Gym or
Gymnasium. You must also include a brief report describing and discussing your solutions to the
problems. Students can do the assignment in groups or individuals.
● This assignment is worth 15% of the total mark for COMP532
● 80% of the assignment marks will be awarded for correctness of results
● 20% of the assignment marks will be awarded for the quality of the accompanying report
● Students will do the assignment in groups
● The assignment marks will be awarded for correctness of results
● We expect 5 students in one group (it would be fine to have groups of 1, 2, 3, and 4 as
well, but it is suggested to have groups of 5), please find your team members on your
own.
● Only one single submission is needed for each group
● The same marks will be granted to all the members in the same group
● Please list all your group members (names, emails, student ids) and individual
contributions in your submitted report
Submission Instructions
● Deadline: 22 Apr 2024 17:00 (UK Time)
● Send all solutions as a single PDF document containing your answers, results, and
discussion of the results. Attach the source code for the programming problems as
separate files.
● Submit your solution via Canvas.
● Penalties for late submission apply in accordance with departmental policy as set
out in the student handbook, which can be found at
https://intranet.csc.liv.ac.uk/student/msc-handbook.pdf and the University Code of
Practice on Assessment, found at
https://www.liverpool.ac.uk/media/livacuk/tqsd/code-of-practice-on-assessment/code_of_
practice_on_assessment.pdf
Problem 1 (80 marks)
Implement a deep reinforcement learning agent for a game or environment of OpenAI Gym or
Gymnasium.
Use the lunar_lander environment:
https://gymnasium.farama.org/environments/box2d/lunar_lander/.
Please plot the learning progress of your method from 0 to 1000 episodes. You can have a
figure to show rewards and another figure to show training loss.
Please use a video or gifs or figures to demonstrate how your agent works.
Prepare a report explaining your solution and containing your results, and discussion of the
results.
Attach the source code as separate files. For example, .ipnb - an ipython notebook file.
Problem 2 (20 marks)
Explain exploration and exploitation for deep reinforcement learning.
请加QQ：99515681 邮箱：99515681@qq.com WX：codinghelp
