The last few years has seen the term "Artificial intelligence" become increasingly ubiquitous: as sensationalised headlines dominate our media and new projects and initiatives use the term in an effort to garner attention. In amongst all this is video games: an industry that has historically used artificial intelligence as means of performance theatre, with a variety of bespoke tools and methodologies designed to support these goals, but in-turn alienating games from other industries given the unique challenges faced. In the last few years AI has seen major breakthroughs in the area of Machine Learning - and more specifically 'Deep Learning' - but what does it do? How does it work? And more importantly, how is it relevant to the video games we make and how we make them? In this talk we're going to establish the state of play for AI and video games: how it has being used up until now, explaining how machine learning differs from 'classical' AI, the risks and opportunties of deep learning, but also some of the more novel innovations and opportunties emerging in corporate and academic research that will shape our working practices and the games we make in the coming years.

Takeaway:

• An overview of common tools, technologies and applications of AI in the video games industry.
• How we can expect to see deep learning impact the games industry in the next 3-5 years. 
• Tools, technologies and collaborations available to smaller studios in the UK and overseas.

Our goal is to deliver a constant stream of high quality interactive stories to the mass market, concentrating on themes with wide appeal rather than genre specific niche audiences. To do this we have to build a frictionless content pipeline that allows our writers to put stories in the hands of our customers as rapidly as possible.

Takeaway:

• Pushing content into data allows streamlined production
• A formal structure on narrative unlocks automated testing and procedural content
• There is a significant and underserved audience for interactive stories

This talk will outline the architecture of the cloud gaming pipeline we developed at Polystream. Attendees will learn why there is a need for an alternative to video streaming and how to virtualise the GPU to stream compressed graphics commands in APIs such as D3D11. We will detail how to stream AAA titles, in under 16 milliseconds, without source changes. A description will be given on how to use Renderdoc for automated graphics testing and how to leverage ISPC to extract the maximum performance out of AVX-512 on cloud servers. We will also discuss the unique challenges and tradeoffs of creating bespoke tools and algorithms for visualizing and compressing real-time GPU data.

Takeaway:

• Detailed technical understanding of the command streaming process and requirements
• Pros and cons of command streaming as a stronger alternative to video streaming for 3D interactive content and applications
• Clarity on cloud architecture for command streaming

Procedural generation is being applied to every game genre, mechanic and system you can think of, but actually sitting down and trying to use it can often be a scary process of unexpected problems, catastrophic failures, and head-scratching statistics and probabilities. If you don't feel like rolling the dice with your game, never fear. In this talk, procedural generation expert and AI researcher Mike Cook will walk you through some useful ways to analyse, troubleshoot and discuss procedural generators, using some of the latest ideas from academic research. We'll look at how to work with designers to clearly specify what we want from a procedural generator, how to analyse generative spaces to find the limits of what your generator can do, and how to use parameter space search to explore the deepest, darkest reaches of your generative system. Along the way we'll also look at why Slay the Spire is a procedural generator, how Spelunky solves its problems by blowing them up, and why the real procedural content is the friends we made along the way. 

Takeaway:

Attendees will learn how to

• Discuss and define evaluation criteria for generated content with designers, and understand why this makes analysis easier.
• Perform expressive range analyses to critically assess and visualise what their generative systems can and cannot do.
• Create better tools that help people visualise and edit generative systems more clearly.
• Take lessons from how other games have solved generative problems, and use them to fix or bypass issues in their own work.

A visual, technical and entrepreneurial adventure through more than two years developing the spiritual successor to Her Story with a highly distributed team. Lizi will present the developmental journey of the project using a visual timeline showing progression of the software as it came into being, all the way through to a description of the small incremental polish that went in at the end. Showing screenshots to demonstrate the iterative process and describing the technical implementation of some specific features. Such as how it was localised into eleven languages, when the gameplay is heavily dependent on the subtitle text and the searches that the players make. As well as how videos are played just as smoothly backwards as they play forwards. All along the way with an underlying nod to the way that Furious Bee works with its clients and operates a profitable business.

Takeaway:

• Gain insight into the journey Telling Lies took from prototype to polished released title.
• Learn about the implementation of Some specific features such as localisation and scrubbing.
• Understand the way Furious Bee develops games for its clients.

Satisfactory is a first-person open-world factory building game with a dash of exploration and combat built using the Unreal Engine. To ensure a game with nearly endless scalability will run on a wide range of hardware requires a great deal of optimization techniques.

Takeaway:

• Optimization techniques
• Troubleshooting performance issues
• Optimization patterns found in open world games

Why would you throw away your entire backend 3 months before launching to your community and rewrite it from scratch? It sounds insane but it was the best decision we made. Come explore the journey why we ditched the popular modern design of microservices and NodeJS and went to an old school C++ hand-coded server. This is not a post mortem but rather a roadmap and argument why I think more developers should take this path.

Takeaway:

• Why reworking your backend is not only possible but a good idea
• Comparison between Microservices and Monolith
• Performance metrics to consider

The benefits of adding machine learning (ML) to your development arsenal are becoming increasingly hard to ignore. Whether used to adapt gameplay to user tastes and improve retention or to automatically create content, done correctly, its effects on both player and developer can be remarkable. But for studios with no prior ML experience, where should devs begin?

In this talk, Andrew Webb, machine learning engineer at vTime, will take delegates from zero to ML hero with the help of a virtual presenter, created during the session using ML avatar generation.

Offering invaluable advice on getting started, Andrew will take you through what is and isn't achievable with current machine learning tech, data acquisition, and how to make use of freely available and state-of-the-art work for your own projects. The talk will also cover how to get ready for your first ML hire, including preparing the data for initial projects and the hardware and resources you’ll need to hit the ground running.

Takeaway:

• Learn what is and isn‚Äôt possible with current machine learning tech
• Find out how to prepare before your first machine learning hire
• Learn how to make use of state-of-the-art open source ML projects