Handbook home
AI Planning for Autonomy (COMP90054)
Graduate courseworkPoints: 12.5On Campus (Parkville)
About this subject
- Overview
- Eligibility and requirements
- Assessment
- Dates and times
- Further information
- Timetable (login required)(opens in new window)
Contact information
Semester 1
Nir Lipovetzky
nir.lipovetzky@unimelb.edu.au
Semester 2
Adrian Pearce
adrianrp@unimelb.edu.au
Overview
Availability | Semester 1 Semester 2 |
---|---|
Fees | Look up fees |
AIMS
The key focus of this subject is the foundations of autonomous agents that reason about action, applying techniques such as automated planning, reinforcement learning, game theory, and their real-world applications. Autonomous agents are active entities that perceive their environment, reason, plan and execute appropriate actions to achieve their goals, in service of their users (the real world, human beings, or other agents). The subject focuses on the foundations that enable agents to reason autonomously about goals & rewards, perception, actions, strategy, and the knowledge of other agents during collaborative task execution, and the ethical impacts of agents with this ability.
The programming language used in this subject is Python. No lectures or workshops on Python will be delivered.
INDICATIVE CONTENT
Topics are drawn from the field of advanced artificial intelligence including:
- Search algorithms and heuristic functions
- Classical (AI) planning
- Markov Decision Processes
- Reinforcement learning
- Game theory
- Ethics in AI planning
Intended learning outcomes
On completion of this subject the student is expected to:
- Apply theoretical concepts of reasoning about actions to single and multi-agent problems
- Be able to analyse, design, and implement automated planning, reinforcement learning, and game theoretic techniques to given problems
- Understand the strengths, weaknesses, and ethical consequences of different approaches for reasoning about action
- Be able to critically evaluate and choose the right technique for different problems in reasoning about action
- Communicate technical solutions about automated planning, reinforcement learning, and game theory
Generic skills
On completion of the subject the students should have the following skills:
- Ability to undertake problem identification, formulation, and solution
- Ability to utilise a systems approach to complex problems and to design and operational performance
- Ability to manage information and documentation
- Capacity for creativity and innovation ability to communicate effectively with both the engineering team and the community at large
Last updated: 8 April 2024
Eligibility and requirements
Prerequisites
Students must meet one of the following prerequisite options:
Option 1
Admission into or selection of one of the following:
- MC-SCICMP Master of Science (Computer Science)
- MC-CS Master of Computer Science
- MC-DATASC Master of Data Science
- 100pt Program course entry point in the MC-IT Master of Information Technology
Option 2
Admission into or selection of one of the following:
- Artificial Intelligence (150pt) specialisation (formal) in the MC-IT Master of Information Technology
- Computing (150pt) specialisation (formal) in the MC-IT Master of Information Technology
- Cyber Security (150pt) specialisation (formal) in the MC-IT Master of Information Technology
- Distributed Computing (150pt) specialisation (formal) in the MC-IT Master of Information Technology
Option 3
One of
Code | Name | Teaching period | Credit Points |
---|---|---|---|
COMP20003 | Algorithms and Data Structures | Semester 2 (On Campus - Parkville) |
12.5 |
COMP20007 | Design of Algorithms | Semester 1 (On Campus - Parkville) |
12.5 |
COMP90038 | Algorithms and Complexity |
Semester 1 (On Campus - Parkville)
Semester 2 (On Campus - Parkville)
|
12.5 |
ENGR30004 | Numerical Algorithms in Engineering |
Semester 2 (On Campus - Parkville)
Semester 1 (On Campus - Parkville)
|
12.5 |
ENGR30003 Numerical Programming for Engineers
Corequisites
None
Non-allowed subjects
None
Recommended background knowledge
SWEN20003 Object Oriented Software Development or COMP90041 Programming and Software Development
Basic understanding of logic and set theory. Basic understanding of introductory probability theory.
Inherent requirements (core participation requirements)
The University of Melbourne is committed to providing students with reasonable adjustments to assessment and participation under the Disability Standards for Education (2005), and the Assessment and Results Policy (MPF1326). Students are expected to meet the core participation requirements for their course. These can be viewed under Entry and Participation Requirements for the course outlines in the Handbook.
Further details on how to seek academic adjustments can be found on the Student Equity and Disability Support website: http://services.unimelb.edu.au/student-equity/home
Last updated: 8 April 2024
Assessment
Semester 1
Description | Timing | Percentage |
---|---|---|
One team-based project, involving 2 to 3 team members, requiring approximately 30 - 40 hours of work per student. ILOs 1 to 5 are addressed in this assignment.
| Week 11 | 30% |
One team-based video presentation of approximately 3-5 minutes duration, involving 2 to 3 team members, each member contributing approximately 6 hours of work. ILOs 1 and 5 are addressed in this team-based assignment.
| Week 12 | 5% |
Two individual programming assignments due in weeks 5 and 8, taking approximately 13-15 hours of work each. ILOs 1 and 2 are addressed in these assignments. Each assignment is worth 10%.
| From Week 5 to Week 8 | 20% |
A 20-minute online quiz in week 6. ILOs 1 to 3 are addressed in this quiz.
| Week 6 | 5% |
One written 2-hour closed book end-of-semester examination. ILOs 1, 3, 4, and 5 are addressed in the exam.
| End of semester | 40% |
Semester 2
Description | Timing | Percentage |
---|---|---|
Assignment 1 - Individual - 10% - due Week 4 (Friday). Intended Learning Outcomes (ILOs) 1 and 2 are addressed.
| Week 4 | 10% |
Assignment 2 - Individual - 5% - due Week 6 (Friday). Intended Learning Outcomes (ILOs) 1 and 2 are addressed.
| Week 6 | 5% |
Pre-competition - Group - 10% - due Week 9 (Friday). 15-20 hours of work per student. Intended Learning Outcomes (ILOs) 1 to 5 are addressed.
| Week 9 | 10% |
Assignment 3 - Group- 35% - due Week 12 (Friday). 40-45 hours of work per student . Intended Learning Outcomes (ILOs) 1 to 5 are addressed.
| Week 12 | 35% |
Closed Book Exam - 40% - exam period. Intended Learning Outcomes (ILOs) 1, 3, 4, and 5 are addressed in the exam.
| During the examination period | 40% |
Last updated: 8 April 2024
Dates & times
- Semester 1
Coordinator Nir Lipovetzky Mode of delivery On Campus (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour tutorial per week Total time commitment 200 hours Teaching period 26 February 2024 to 26 May 2024 Last self-enrol date 8 March 2024 Census date 3 April 2024 Last date to withdraw without fail 3 May 2024 Assessment period ends 21 June 2024 Semester 1 contact information
Nir Lipovetzky
nir.lipovetzky@unimelb.edu.au - Semester 2
Coordinator Adrian Pearce Mode of delivery On Campus (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour tutorial per week Total time commitment 200 hours Teaching period 22 July 2024 to 20 October 2024 Last self-enrol date 2 August 2024 Census date 2 September 2024 Last date to withdraw without fail 20 September 2024 Assessment period ends 15 November 2024 Semester 2 contact information
Adrian Pearce
adrianrp@unimelb.edu.au
Time commitment details
200 hours
What do these dates mean
Visit this webpage to find out about these key dates, including how they impact on:
- Your tuition fees, academic transcript and statements.
- And for Commonwealth Supported students, your:
- Student Learning Entitlement. This applies to all students enrolled in a Commonwealth Supported Place (CSP).
Subjects withdrawn after the census date (including up to the ‘last day to withdraw without fail’) count toward the Student Learning Entitlement.
Last updated: 8 April 2024
Further information
- Texts
Prescribed texts
- Subject notes
LEARNING AND TEACHING METHODS
The subject involves two 1-hour lectures per week followed by a 1 one hour workshop with interactive lab and discussion activities. A significant amount of project work is open ended, encouraging self assessment and hands-on experience to explore the breadth of topics covered.
INDICATIVE KEY LEARNING RESOURCES
Students will have access to lecture notes, slides, videos and interactive programming notebooks with worked solutions. Most programming will be based on python interfaces.
CAREERS / INDUSTRY LINKS
Planning is a key capability for industries that require dynamic autonomy and reasoning, from conversational agents to robotic platforms. Key industry players are space and underwater exploration agencies, as well as IBM, Google and other IT that hold R&D groups.
- Related Handbook entries
This subject contributes to the following:
Type Name Course Doctor of Philosophy - Engineering Course Ph.D.- Engineering Course Master of Science (Computer Science) Course Master of Philosophy - Engineering Course Master of Data Science Specialisation (formal) Software Specialisation (formal) Mechatronics - Available through the Community Access Program
About the Community Access Program (CAP)
This subject is available through the Community Access Program (also called Single Subject Studies) which allows you to enrol in single subjects offered by the University of Melbourne, without the commitment required to complete a whole degree.
Entry requirements including prerequisites may apply. Please refer to the CAP applications page for further information.
Additional information for this subject
Subject coordinator approval required.
- Available to Study Abroad and/or Study Exchange Students
This subject is available to students studying at the University from eligible overseas institutions on exchange and study abroad. Students are required to satisfy any listed requirements, such as pre- and co-requisites, for enrolment in the subject.
Last updated: 8 April 2024