Handbook home
AI Planning for Autonomy (COMP90054)
Graduate courseworkPoints: 12.5On Campus (Parkville)
For information about the University’s phased return to campus and in-person activity in Winter and Semester 2, please refer to the on-campus subjects page.
About this subject
- Overview
- Eligibility and requirements
- Assessment
- Dates and times
- Further information
- Timetable(opens in new window)
Contact information
Semester 1
Chris Ewin
Semester 2
Dr Nir Lipovetzky
Please refer to the LMS for up-to-date subject information, including assessment and participation requirements, for subjects being offered in 2020.
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: 3 November 2022
Eligibility and requirements
Prerequisites
- Be admitted into the 100 pt program of the MC-IT (Master of Information Technology)
- Be admitted into the 150 pt program of the MC-IT Artificial Intelligence, Computing and Distributed Computing Specialisations
- Be admitted into the Master of Science (Computer Science)
- Be admitted into the Master of Computer Science MC-CS
- Be admitted into the Master of Data Science MC-DATASC
Code | Name | Teaching period | Credit Points |
---|---|---|---|
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 |
COMP20003 | Algorithms and Data Structures | Semester 2 (On Campus - Parkville) |
12.5 |
ENGR30003 | Numerical Programming for Engineers | Semester 2 (On Campus - Parkville) |
12.5 |
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: 3 November 2022
Assessment
Due to the impact of COVID-19, assessment may differ from that published in the Handbook. Students are reminded to check the subject assessment requirements published in the subject outline on the LMS
Description | Timing | Percentage |
---|---|---|
Two programming-based assignments (15% combined), due in weeks 4 and 8, taking approximately 13 - 15 hours of work each, including preparation. Intended Learning Outcomes (ILOs) 1 and 2 are addressed in these assignments.
| From Week 4 to Week 8 | 15% |
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% |
One written 2-hour closed book end-of-semester examination. ILOs 1, 3, 4, and 5 are addressed in the exam.
| During the examination period | 50% |
Additional details
Last updated: 3 November 2022
Dates & times
- Semester 1
Principal coordinator Chris Ewin Mode of delivery On Campus (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour workshop per week Total time commitment 200 hours Teaching period 2 March 2020 to 7 June 2020 Last self-enrol date 13 March 2020 Census date 30 April 2020 Last date to withdraw without fail 5 June 2020 Assessment period ends 3 July 2020 Semester 1 contact information
Chris Ewin
- Semester 2
Principal coordinator Nir Lipovetzky Mode of delivery On Campus (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour workshop per week Total time commitment 200 hours Teaching period 3 August 2020 to 1 November 2020 Last self-enrol date 14 August 2020 Census date 21 September 2020 Last date to withdraw without fail 16 October 2020 Assessment period ends 27 November 2020 Semester 2 contact information
Dr Nir Lipovetzky
Time commitment details
200 hours
Last updated: 3 November 2022
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 held in a computer laboratory. Weekly readings are assigned from textbooks, and weekly laboratory exercises are assigned. A significant amount of project work is assigned.
INDICATIVE KEY LEARNING RESOURCES
At the beginning of the year, the coordinator will propose textbook(s) on computer graphics and interaction and will be made available through the University Book Shop and library. Students will have access to lecture notes and lecture slides. The subject CANVAS site also contains links to recommended literature and current survey papers of software agent principles.
CAREERS / INDUSTRY LINKS
The IT industry is a large and steadily growing industry and advanced artificial intelligence techniques such as software agents are increasingly an integral part of the many facets of this industry. The University of Melbourne and Microsoft have created a new teaching innovative, Apps@Melbourne, for the many talented students keen on developing Apps for tablet computers. Students enrolled in this subject have the opportunity to publish Apps they have developed on the store to be made available to the wider community.
- Related Handbook entries
This subject contributes to the following:
Type Name Course Master of Science (Computer Science) Course Master of Data Science Course Doctor of Philosophy - Engineering Course Ph.D.- Engineering Course Master of Philosophy - Engineering Specialisation (formal) Computing Specialisation (formal) Distributed Computing 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: 3 November 2022