Multi-Agent Reinforcement Learning Research Proposal

Lead Research Organisation: University of Oxford


1 Research Context and Impact
Recent progress in artificial intelligence promises a future where humans co-exist with autonomous intelligent systems. However, a key requirement for such a future is that autonomous agents are able to co-operate with not
only humans but also other autonomous agents. Co-operative Multi-Agent Reinforcement Learning aims to enable autonomous agents to co-operate with one another towards a common goal. This has applications to areas such as
autonomous vehicles and the automation of manual tasks performed in a team. We aim to contribute to this area by developing a benchmark that can be used to compare different multi-agent reinforcement learning algorithms.
2 Aims and Objectives
Benchmarks for multi-agent reinforcement learning have a number of benefits. First, they provide a standard set of tasks that researchers can use to compare the performance of different algorithms and approaches. Secondly,
they allow progression to real-world applications by providing simplified versions that can be solved in simulation. However, pre-existing benchmarks have largely been solved and no longer provide a suitable level of complexity.
Additionally, they have at their heart a number of restrictions that limit their complexity. We aim to provide a benchmark that lifts some of these restrictions.
3 Novelty of Research Methodology
One of the most popular benchmarks, the Starcraft Multi-Agent Challenge, has a computer-controlled set of enemies with a fixed policy, limited partial observability and allows all of the agents performing the task to be trained together
as a team. These restrictions would not hold in a real system because deployment environments can change, new versions of agents would have to co-exist with agents from other manufacturers, and agents may have work hard
to infer the intention of agents whose observations they do not know. We will work to understand which of these challenges are best able to be tackled at present by the multi-agent reinforcement learning community and then
design and propose a task that entails solving these problems.
4 Alignment to EPSRC's strategies and research areas
AI Technologies EPSRC research area

Planned Impact

AIMS's impact will be felt across domains of acute need within the UK. We expect AIMS to benefit: UK economic performance, through start-up creation; existing UK firms, both through research and addressing skills needs; UK health, by contributing to cancer research, and quality of life, through the delivery of autonomous vehicles; UK public understanding of and policy related to the transformational societal change engendered by autonomous systems.

Autonomous systems are acknowledged by essentially all stakeholders as important to the future UK economy. PwC claim that there is a £232 billion opportunity offered by AI to the UK economy by 2030 (10% of GDP). AIMS has an excellent track record of leadership in spinout creation, and will continue to foster the commercial projects of its students, through the provision of training in IP, licensing and entrepreneurship. With the help of Oxford Science Innovation (investment fund) and Oxford University Innovation (technology transfer office), student projects will be evaluated for commercial potential.

AIMS will also concretely contribute to UK economic competitiveness by meeting the UK's needs for experts in autonomous systems. To meet this need, AIMS will train cohorts with advanced skills that span the breadth of AI, machine learning, robotics, verification and sensor systems. The relevance of the training to the needs of industry will be ensured by the industrial partnerships at the heart of AIMS. These partnerships will also ensure that AIMS will produce research that directly targets UK industrial needs. Our partners span a wide range of UK sectors, including energy, transport, infrastructure, factory automation, finance, health, space and other extreme environments.

The autonomous systems that AIMS will enable also offer the prospect of epochal change in the UK's quality of life and health. As put by former Digital Secretary Matt Hancock, "whether it's improving travel, making banking easier or helping people live longer, AI is already revolutionising our economy and our society." AIMS will help to realise this potential through its delivery of trained experts and targeted research. In particular, two of the four Grand Challenge missions in the UK Industrial Strategy highlight the positive societal impact underpinned by autonomous systems. The "Artificial Intelligence and data" challenge has as its mission to "Use data, Artificial Intelligence and innovation to transform the prevention, early diagnosis and treatment of chronic diseases by 2030". To this mission, AIMS will contribute the outputs of its research pillar on cancer research. The "Future of mobility" challenge highlights the importance the autonomous vehicles will have in making transport "safer, cleaner and better connected." To this challenge, AIMS offers the world-leading research of its robotic systems research pillar.

AIMS will further promote the positive realisation of autonomous technologies through direct influence on policy. The world-leading academics amongst AIMS's supervisory pool are well-connected to policy formation e.g. Prof Osborne serving as a Commissioner on the Independent Commission on the Future of Work. Further, Dr Dan Mawson, Head of the Economy Unit; Economy and Strategic Analysis Team at BEIS will serve as an advisor to AIMS, ensuring bidirectional influence between policy objectives and AIMS research and training.

Broad understanding of autonomous systems is crucial in making a society robust to the transformations they will engender. AIMS will foster such understanding through its provision of opportunities for AIMS students to directly engage with the public. Given the broad societal importance of getting autonomous systems right, AIMS will deliver core training on the ethical, governance, economic and societal implications of autonomous systems.


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S024050/1 30/09/2019 30/03/2028
2416682 Studentship EP/S024050/1 30/09/2020 29/09/2024 Benjamin Ellis