Deep Reinforcement Learning with Logical Specifications

Context and objectives of the research:
Reinforcement learning (RL) is a fundamental technique that enables agents to learn desirable behaviour through interactions with an unknown environment. Recent years have witnessed outstanding advances in the field, and it has been applied with great success in a variety of contexts such as traffic control, energy management, video games, and autonomous driving. However, despite these successes it remains a challenging problem to learn behaviour that can generalise across multiple different tasks. One of the fundamental problems in this setting is how to specify tasks such that skills applicable to multiple subtasks can be effectively leveraged. Recent works have made progress in this direction by using linear temporal logic (LTL) as a language to formally specify tasks. The objective of this research is to build upon these recent works and develop novel algorithms to allow agents to learn general behaviour with well-specified semantics. We will focus especially on integrating techniques from formal verification that allow for high-level reasoning about the task structure. At later stages of the project, we aim to investigate architectures that integrate LTL specifications with image observations, as well as more involved RL techniques such as model-based and safe RL.

Novelty of the research methodology:
This research builds upon recent works in the area. However, in contrast to previous works we especially focus on the efficiency and safety of agents, which is an important real-world concern that impacts our algorithmic choices. We also put more emphasis on the integration of techniques from formal methods than previous approaches. Furthermore, our proposed extensions, such as combining general LTL instructions with image observations, remain largely underexplored.

Alignment to EPSRC research areas:
The proposed project aligns with the research areas Artificial Intelligence Technologies and Verification and Correctness.

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.