COMP0124 Multi-agent Artificial Intelligence

This database contains the 2018-19 versions of syllabuses.

Note: Whilst every effort is made to keep the syllabus and assessment records correct, the precise details must be checked with the lecturer(s).

Academic session

2018-19

Module

Multi-agent Artificial Intelligence

Code

COMP0124

Module delivery

1819/A7U/T2/COMP0124 Masters (MEng)

Related deliveries

1819/A7P/T2/COMP0124 Postgraduate

Prior deliveries

COMPM041

Level

Masters (MEng)

FHEQ Level

L7

FHEQ credits

15

Term/s

Term 2

Module leader

Wang, Jun

Contributors

Wang, Jun

Module administrator

Ball, Louisa

Aims

The course is intended to provide an introduction of multi-agent machine learning, a subfield of Artificial Intelligence (AI). Multi-agent learning arises in a variety of domains where multiple intelligent computerised agents interact not only with the environment but also with each other. There are an increasing number of applications ranging from controlling a group of autonomous vehicles/drones to coordinating collaborative bots in factories and warehouses, optimising distributed sensor networks/traffic, and machine bidding in competitive e-commerce and financial markets, just to name a few. The module combines the study of machine learning with that of game theory and economics, including topics such as game theory, auction theory, algorithmic mechanism design, multi-agent (deep) reinforcement learning. Practical applications, including online advertising, online auction, adversarial training for generative models, bots planning, and AI agents playing online games, will also be covered and discussed.

Learning outcomes

On successful completion of the module, the students will be able to master both the theoretical and practical aspects of module. Specifically, the students will understand the underlying principle and the theory for decision making by multiple parties, and the learning algorithms that obtain optimal decision or reach an equilibrium with multiple incentives. The students are also expected to be able to make use of the learned theory and algorithms to formulate and solve large-scale practical learning problems where multiple objectives/incentives co-exist.

Availability and prerequisites

This module delivery is available for selection on the below-listed programmes. The relevant programme structure will specify whether the module is core, optional, or elective.

In order to be eligible to select this module as optional or elective, where available, students must meet all prerequisite conditions to the satisfaction of the module leader. Places for students taking the module as optional or elective are limited and will be allocated according to the department’s module selection policy.

Programmes on which available:

  • MEng Computer Science (International Programme) (Year 4)
  • MEng Computer Science (Year 4)
  • MEng Mathematical Computation (International Programme) (Year 4)
  • MEng Mathematical Computation (Year 4)

Prerequisites:

In order to be eligible to select this module, students must have:

  • a strong competency in programming in Python/Java (evidence of at least one past programing project is required);
  • a strong competency in probability and statistics; and
  • basic knowledge of machine learning and deep learning concepts and algorithms, e.g., classification, regression and clustering (evidence of at least one past programming project using TensorFlow, PyTorch, MXNet or similar deep learning frameworks is required)

Content

Game theory and online auction

  • The prisoner‘s dilemma, dominant strategy, Nash equilibrium, Mixed strategies, and Pareto optimality;
  • English Auctions, Dutch Auctions, the first price auctions, and the second price auctions

Learning Nash Equilibria and Learning in Repeated Games

  • The linear programing solution and the Lemke-Howson algorithm

Single-agent Reinforcement Learning

  • Value Iterations, Policy Iterations, Q-learning, Policy Gradient, and Deep Reinforcement Learning

Multi-agent reinforcement learning

  • Stochastic games, Nash-Q, Gradient Ascent, WOLF, and Mean-field Q learning

Applications:

  • Online advertising machine bidding, AI agents playing online games, and learning to collaborate for bots

Reference books

Shoham, Yoav, and Kevin Leyton-Brown. Multiagent systems: Algorithmic, game-theoretic, and logical foundations. Cambridge University Press, 2008.

An indicative reading list is available via http://readinglists.ucl.ac.uk/departments/comps_eng.html.

Delivery

Lectures. Occasionally guest lectures by leading researchers or industry practitioners in the field. A website or/and Moodle webpage will be created for the course and the course materials, such as lecture notes, sample codes, will be shared.

Assessment

This module delivery is assessed as below:

#

Title

Weight (%)

Notes

1

Group project report

50

An alternative LSA assessment will be an extended individual project based on the group project already submitted.

2

Individual report

50

 

In order to pass this module delivery, students must:

  • achieve an overall weighted module mark of at least 50%; and
  • achieve a mark of at least 40% in any components of assessment weighed ≥ 30% of the module.

Where a component comprises multiple assessments, the minimum mark applies to the overall component.