Conference Programme
Thursday 7th - Welcome Reception & Networking
Friday 8th - Two Tracks of Talks
We'll be announcing our schedule soon.
- Thursday 7th November
- Friday 8th November
- Speaker/Sponsor Reception
A drinks reception for our speakers and sponsors to network, test their talks in the venue, and grab their passes prior to the big event!
- Room 1
- Room 2
A few words from our organisational team as we welcome you to the inaugural AI and Games Conference.
Note: This will run in Room 1, with the presentation being streamed into Room 2 via a live feed.
This talk is about Decima’s implementation of HTN. We will give a short history of our implementation and talk about how it integrates with the rest of our AI system. We compare it to behaviour trees and some other HTN implementations. We explain how our implementation performs backtracking (similar to Prolog) over preconditions and present a flow visualization which can help understand the backtracking flow, This talk will detail how that flow is realized in generated C++ and also touch on how we debug our HTN decompositions in-game.
Takeaways:
- Attendees will learn how HTN with backtracking can be realized in (generated) C++ code.
- Learn about a specific flow visualization (inspired by the “Byrd Box model” for Prolog) and how it can help understand backtracking flow.
- Learn how an HTN decomposition can be logged and how these logs can be displayed.
Description: Avalon is a new method designed to enhance level generation by providing more control over the generation process, while ensuring the creation of more solvable levels. In particular, we generate layouts of match-3 levels where the level designers can select visual features like size and symmetry and gameplay statistics such as difficulty. We will describe how we designed the system, how it compares to other methods and the quantitative and qualitative analysis performed on it. We will finalize with a brief discussion about challenges and opportunities of level generators in production.
Takeaways:
- How to create controllable (conditional) generators for match3 games
- How to take advantage of that controllability to improve the validity of the levels
- Challenges and opportunities of level generators in production
Take 20 minutes to stretch your legs, grab a coffee and decide what talks to check out next!
This talk delves into how language models transform story narratives into fully realized game worlds. Starting with a story, we generate an entire game world including detailed maps, locations, and objects that align with the narrative. Furthermore, the world is populated with dynamic characters that have evolving memories, relationships, and behaviors shaped by the narrative. This approach can potentially complement existing generation tools to leverage the strength of different techniques.
The talk will feature a Murder Mystery demo, demonstrating an end-to-end generation pipeline going from story to a playable game, resulting in a meaningful generated world that reflects the intricate relationship between story, environment, and character evolution.
Takeaways:
- Using LLMs for narrative-driven generation for game development
- Combine LLMs with game mechanics to drive dynamic NPC behaviors
- Use cases where LLMs are most effective as a generation tool, along with practical tips and strategies
We’ll explore the promise and challenges of using generative techniques to create new experiences in established worlds. Large language models are a fraught technology, including in their lack of regard for the boundaries of intellectual property. At Hidden Door, we’ve been combining them in constrained ways with procedural generation, templating, and “classical” natural language techniques to allow stories that feel meaningfully different every time, but which respect the world in which they occur.
We’ll speak to the kind of input that creative partners (authors, film producers, and other creators) want, and discuss the risks and pitfalls of generative technology (oh hi, bias) and how we mitigate those. We can also share how we’ve approached these challenges in our game, with examples like:
- Using language models to choose which templated story beat happens next, instead of generating them from scratch.
- Treating language as a unique affordance for player characters (my strong character is different than your strong character).
- Creating lots of content using procgen and language models together, with a game designer’s curation.
- When we take the reigns off and let worlds get weird (cybernetic mech skeleton in the Wizard of Oz?).
- How to do this ethically, from a technology, data, and business perspective.
Takeaways:
- A grounded perspective on the use of large language models: both boons and pitfalls.
- Some approaches to mitigating bias when using those models.
- Examples of non-LLM machine learning techniques and their use in generative stories.
In Rain World, we used AI as an fundamental building block for our core game loop. The game is essentially about interacting with AI and AI agents interacting with each other. In this talk we give a breakdown of the systems employed and how this enabled for the design of Rain World to be achieved.
Takeaways:
- Multiple AI agents interacting will be unpredictable
- The level at which you comminicate what’s going on inside an AI agent is a delicate decision, with upsides and downsides to both extremes
- Making AI and emergent behaviour the core feature of your game will almost definitely make it “interesting” rather than “smooth”
Machine learning for non-player character control is often unwieldy and takes a lot of time. In this talk we will share some reliable design patterns I have learnt researching and developing learning agents from collaborations on Age of Empires 4, Bleeding Edge, Minecraft and more.
Takeaways:
- A method to stabilise reinforcement learning to reliably improve Non-Player Character (NPC) performance;
- A simple way to make the NPC’s learnt behaviour more human-like;
- How to combine both to make NPC’s collaborate with any human player.
Implementing AI for tactical games is challenging, especially when the AI opponent must make decisions akin to a human player and provide a challenge in a one-on-one match. And if you add geometric considerations like planning for movement of physical objects, you get a recipe for an AI programmer’s headache. However, with the right tools, nothing is impossible! This presentation showcases a case study on AI bots developed for the unique tactical sports game, Soccer Kids by Acid Wizard. It will be invaluable for AI programmers, particularly those interested in strategic and tactical genres.
Takeaways:
- Post-mortem of a unique game.
- Introduction to Monte Carlo Tree search.
- Handling physical collisions and other geometric aspects in MCTS simulations.
- Tips and tricks for spatial analysis used for determining possible unit movements in a continuous space and evaluating the overall tactical situation.
In this talk we explore the AI design philosophy for Space Marine 2, our various solutions that helped to achieve the desired vision and overcome obstacles. As well as a brief introduction of our AI framework implementation.
Takeaways:
- Opportunistic and Reactive AI design and techniques
- A way to approach Many vs Many combat scenarios
- Moveset and behaviour design with Player Gameplay Graph approach
- Why Behaviour Trees and Utility AI make a great mix
Description: A continuation and recontextualization of my 2024 GDC AI Summit talk “How ‘Ara: History Untold’ Transformed AI in 4X Games”, I will summarize Ara: History Untold’s novel system, and dig into details around optimizing its performance, and usability in the final months leading up to ship.
Takeaways:
- An introduction to semi-obscure but very useful AI topics (HGNs, Logical DSLs)
- Insights into making performant data structures for complex game AI
- Practical examples of how to make trades between effectiveness and complexity
The talk gives an overview of components used to build the AI behavior of machines for Horizon Forbidden West. It follows the examples of the Waterwing from the Burning Shores DLC, a semi-aquatic flying machine that fights the player in any medium it encounters them in. The talk will cover topics such as in-air and underwater navigation and movement, and combat behaviors. Most other AI characters in the game share these components.
Takeaways:
- Gain insight into what goes into building the AI behavior of the Waterwing. These parts generalize to the other machines built for Horizon Forbidden West.
- Learn about the navigation and movement solutions used in Horizon Forbidden West in-air and underwater.
- Learn about the AI components used to build challenging machines to fight against.
All good things must come to an end!
A few words from our organisational team as we welcome you to the inaugural AI and Games Conference.
Note: This will run in Room 1, with the presentation being streamed into Room 2 via a live feed.
Multi-agent systems expand the overall capabilities of generative AI applications. By enabling multiple generative AI agents to work together, performing separate tasks, and leveraging different tools, these systems automate the identification and execution of robust tasks. By distributing complex tasks among specialized agents, multi-agent systems address coordination and communication challenges when working with multiple models. Learn how AWS utilized open source tools and native AWS AI Services to build an “Idea to Game Code”, Multi-Agent System. You’ll see a demo of the system hosted on AWS and dive into how agents work, how they work together, and tips to get started building your own agents.
Takeaways:
- An understanding of how generative AI agents work and how they can work together to form a multi-agent system.
- Tips on how to get started building your own agents.
- Considerations when building agentic systems.
The talk will give a user-friendly overview of the key legal risks arising from the use of AI in videogames together with practical advice on how to mitigate these risks. We’ll cover issues like the state of the law at present (e.g. the UK’s approach vs the EU AI Act), how to avoid common legal traps when using AI (e.g. infringement) and how to protect your own IP.
Takeaways:
- An understanding of the regulatory landscape when it comes to using AI in video games
- How to protect a studio’s existing IP when using AI
- How to safely use the outputs generated by AI
Take 20 minutes to stretch your legs, grab a coffee and decide what talks to check out next!
This talk will take you step by step through the key IP issues that can arise when using AI tools, how to navigate these issues and mitigate the potential risks. This talk will provide a toolkit to help you understand, in practical terms, how to approach use of these tools while still ensuring that your IP, your confidential information, your data and game remain protected.
Takeaways:
- Gain a high level understanding of the key intellectual property issues that can arise in connection with use of AI tools (and specifically generative AI tools.
- Understand which aspects of your business and of the game development process are most at risk when using AI tools.
- Learn how to mitigate these risks and come away with a checklist of practical steps for protecting your IP when developing and releasing a game.
Description: The complexity of modern tabletop games has been steadily increasing since the mid-1990s. This results in an increase in time spent by designers developing (2-3 years on average from idea to commercialisation) and playtesting (6-24 months) a game, raising the barrier of entry to market for independent designers or small companies which do not have enough resources at their disposal. The effect is also felt by players, who find it harder to play such games due to the steep learning curve. This talk will explore how Tabletop R&D, a spin-out company from Queen Mary University of London, aims to address these issues and democratize the tabletop games market by providing game designers with automatic playtesting tools. Using the latest in Game AI technology and digital twins of tabletop games, we speed up development times, reduce costs and increase efficiency of an otherwise traditionally lengthy analogue process.
Takeaways:
- How to use automatic play-testing with AI agents.
- Learn about a diverse set of metrics to evaluate game-play experience.
- The value of exploring the design space of your game.
Learning Agents is an Unreal Engine plugin that enables you to train AI characters using machine learning (ML).
In this session, we’ll explore how the plugin can be used to augment or replace traditional game AIs such as those written with behavior trees or state machines.
In particular, the plugin enables you to use reinforcement (RL) and imitation learning (IL) approaches. Join to discover how Learning Agents could have a range of applications in the long term, including for physics-based animation, game-playing NPCs, and automated QA testing.
Takeaways:
- How Learning Agents Works
- How we applied Learning Agents to aiming in Fortnite
- What sort of problems is Learning Agents useful to explore.
Description: The Battlefield QV department manages an automated issue workflow that handles reports coming from diverse data sources and entities, such as error APIs, automation systems, etc. An important part of this workflow is the interaction with the issue tracking manager Jira, where tickets are created automatically using data retrieved from the reports. The process is not fully automated, as there are still parts that require the hardcoding of rules that may change over time or a manual intervention that can become time consuming when the volume of tickets reaches high peaks. The talk explores the potential of Large Language Models (LLMs) in automated issue management within the Battlefield franchise. It has the goal to address the identification of duplicate issues, replacing the inefficiency of the previous hardcoded rules. We will demonstrate how the same solution based on LLMs could also be reused in all the projects utilizing the same version of Frostbite (our engine). Furthermore, the talk discusses the challenges and best practices of integrating a research project into an established game development workflow, and how to overcome these challenges.
Takeaways:
- How to leverage the potential of LLMs for specific use cases in game development, particularly in QA.
- Insights into real-world QA improvements achieved through the use of LLMs compared to traditional approaches, along with the challenges in measuring these improvements.
- An understanding of the challenges and opportunities associated with using machine learning in game production, and how to effectively combine research and development efforts.
Discover how you can develop faster with a little help from AI with Muse. Solve problems with Chat, get solutions tailored to your unique project settings, and automatically carry out tasks within the editor.
Takeaways:
- Discover how we made Muse directly available in the editor and gave it contextual awareness.
- Learn how you can leverage Muse to get tailored solutions and perform actions in your project.
- Get a glimpse of Unity’s vision on how AI can assist Game development for faster creation with less friction.
Description: Training RL agents in games requires collecting lots of data from various game states and trajectories. As games grow in complexity, it is easy for some unintended functionality to affect the distribution of data that an RL agent would be trained on. This means an agent’s behaviour may be affected and ultimately be a signal that some property of the game does not match intentions. This matches the criteria for a property based test and is an inspiration for future game testing mechanisms.
Takeaways:
- An intuition of property based testing.
- A concrete example of how RL training helped identify a bug
- An inspiration for how RL training can be more incorporated into property tests
We discuss the current state of the industry, and how things will progress as AI technologies continue to evolve.
This talk will expose the secret practice of restraining AI agents to bounded areas of the game world. We’ll see why this is often a desired feature in terms of game design. We’ll also go over the possible implementation approaches, how they can be mixed, and their performance implications.
Takeaways:
- Understanding of what NPC tethering is
- Realization that it’s deeply dependent on game design
- Some ideas on how to implement agent tethering into your own projects.
Description: What are the challenges in writing an AI that can generate an interesting settlement adapted to an unseen Minecraft map? What AI techniques work well here? These are just some of the questions the GDMC AI settlement generation challenge set out to answer when it was founded 7 years ago. Adaptive and holistic procedural content generation in games still has many open challenges, and in this talk we will take a look at some selected ideas and AI techniques used to tackle those. I will show a range of colorful and amazing settlement generators, and discuss what worked and what did not. If you feel after the talk that you could do better, I have great news for you, we will be back in 2025 for round 8.
Takeaways:
- Learning about the GDMC competition – a fun AI programming competition.
- The use of AI competition to drive research and find out things.
- A comparison of different AI approaches to the same problem.
- A better understanding of the problems of adaptive PCG.
Computing the position of objects in a game is one of the most frequent features to be carried out: where to stop a movement (to avoid a collision)? Where to hide, protect or start a jump? Where do two zones intersect (which objects will be affected by the zone of effect of my action)?
The goal of this presentation is to suggest that solving the analytical geometry equations resulting from the various game situations is preferable to using the various environment projection queries provided by your favourite game engine: first write the equations to which the coordinates of the game objects must conform, then solve these equations to obtain the numerical values of these coordinates; and don’t forget to get help from a math software. These two steps will be illustrated in the case of projecting a grid onto a navigation surface for the Unreal Engine with the help of Mathematica.
Takeaways: This presentation is intended for AI game developers facing one of the three situations:
- Too much computing resources are spent generating sample locations and then filtering them
- Write and solve the equations modelling the geometric problem
- Too many erroneous or approximate locations require post-processing to be usable
- Compute values from exact solutions of your geometric problems
- Bullet proofs tests of locations are needed
- Compare locations with exact solutions of your geometric equations
All good things must come to an end!