Real-time Decisions (Day #1)

Join experts from the games and mobile industry, leading researchers for a day-long course on state-of-the-art techniques in decision making from evolutionary algorithms to Deep Learning with neural networks, why and how they can be applied in interactive applications.

Now in its 8th edition, nucl.ai brings together hundreds of developers from creative industries and interactive media to resolve the biggest technical and design problems with Artificial Intelligence. One of the event's tracks focuses specifically on “Real-time Decisions” for an entire day.
(Day #1: Monday, July 18th)

Regular & Current Attendees

  • Ubisoft Montreal
  • CD Projekt Red
  • Creative Assembly
  • Bohemia Interactive
  • Epic Games
  • Iron Galaxy Studios
  • MASA Group
  • Square Enix
  • Microsoft Game Studios
  • University of Essex
  • Unity Technologies
  • INRIA Research Lab
  • University of Muenster
  • CCP Games
  • ...

I've never seen so many industry figures, academics, and students happy to discuss a range of topics around AI in games. It was really, REALLY helpful.

Matthew Bedder

PhD Student

University of York, UK

It was great to return to #nuclai15 this year, I met loads of interesting people and came away buzzing with new ideas.

Vicky Smalley

CTO

Small Jelly, UK

It was my first time at #nuclai15 and I heard about it very late through co-workers. I was mostly interested in the Character Animation panels. I really hope to be able to attend every year from now on! Great information, great people, great time!

Laurent Delayen

Senior Gameplay Programmer

Epic Games, USA

For the first time in my life, I left a conference with concrete and crystallized plans to improve my current project based on the talks I attended and the conversations I had with people. Incredibly. Useful.

Sergey Mohov

Game Designer

Tequila Works, SPAIN

First time visiting a conference like this, and #nuclai15 made a very strong first impression. Great sessions, great people, great time!

Aaron Oostdijk

Lecturer & Researcher

University of the Arts Utrecht, NETHERLANDS

An invaluable resource of ideas and enthusiasm. Long may it continue.

Jim Brewster

Technical Lead

NaturalMotion, UK

Spent months of saving and talking to Alex on twitter – it was more than worth it. I cannot express how this experience changed me and might as well have shaped my future. From the networks I've created to the feedback needed to get back on track I am extremely happy for this opportunity and #nuclai16 is on my calendar.

Mohamed Serry

Gameplay Programmer

Creability, UNITED ARAB EMIRATES

#nuclai15 was really unique and cross-discipline, bringing feature film, game AI, animation and machine learning people and talks together makes it the perfect opportunity to learn for everyone.

Alexander Shafranov

Animation Programmer

Remedy Games, FINLAND

Inspiring talks, dedicated people, things to play with, that's a conference to my taste.

Anika Uhlemann

Engine & Game Programmer

GOODGAME Studios, GERMANY

Attending conferences like Nucl.ai brings me in the perfect mental state. I always try to invent something crazy in the plane back home...

Simon Clavet

Animation & Physics Programmer

Ubisoft Montreal, CANADA

Wide variety of topics, great speakers, interesting conversations and lots of very very cool stuff to see and try - Nucl.ai easily beats other conferences!

Kevin Schmidt

Head of Data Science

Mind Candy, UK

#nuclai15 was again a wonderful opportunity to focus on game AI and the intersection of game design and programming. Great talks and great conversations.

Jurie Horneman

Independent, FRANCE



How do you build your simulation to respond to user input at interactive rates, especially if it needs to make intelligent decisions? Artificial intelligence techniques have evolved significantly over the past few years, allowing you to make choices about complex problem domains with any-time algorithms. If you're creating intelligent runtime agents for your games, simulations or applications, this track will help you make the most of recent advances.

Keywords

  • utility systems
  • monte-carlo tree search
  • deep neural networks
  • tactics and strategy

Format

  • Keynote
  • Presentations
  • Panel Discussion
  • Expert Q&A

Track Schedule (Day #1: Monday, July 18th)

Track Schedule (Day #1: Monday, July 18th)

Day #1: Monday, July 18th

Real-time Decisions

Dynamic Dialog & Storytelling

Human Interaction & Recognition

Niels Justesen, IT University Copenhagen

09:15 Online Evolution for Hero Academy and Multi-Action Games (Academy)

Tristan Cazenave, Université Paris Dauphine

10:00 Computer Go: from Influence Functions to AlphaGo (Amphitheatre)

Wojciech Jaśkowski, Poznań University of Technology

16:00 Hands-On Deep Q-Learning in DOOM [Workshop] (Open Labs)

Wojciech Jaśkowski, Poznań University of Technology

14:15 Advances in Deep Reinforcement Learning (Academy)

Tickets!

Join developers from all over the world and secure your ticket for this year's nucl.ai now! Three days of artificial intelligence theory and practice packed into three parallel tracks per day with many networking opportunities are waiting for you in Vienna.

Conference* (3 Days)

All Content* (3 Days)

Single Day Ticket

Early Bird

A limited number of these tickets was available.

Sold Out.

Sold Out!

-

Early Worm

These tickets were available for a limited time.

Expired.

Sold Out.

-

Regular

Important: All Access sold out. All Content available instead.*

€ 369

€ 999

€ 399

Student Pass**

Available until Friday July 8th

60% off above

60% off above

60% off above

Indies or Unemployed Devs***

Available until Friday July 8th

20% off above

30% off above

20% off above

* All Access tickets give you access to all rooms on all days of the conference, Single Day tickets give you full access, but only on the day of your choice. With a main conference ticket you can access the amphitheatre and the open laboratories. See here for more details about ticket types and discounts.

Keynotes and Presentations

It's All about Location: Expanding the Frontier of Spatial Query Systems in RPGs

As spatial query systems such as EQS (Unreal Engine 4), TPS (CryEngine), and PQS (Luminous Studio) have matured, auto-generated spatial queries are increasingly relied upon for robust dynamic position selection. We present a series of techniques and extensions to these systems used by Square Enix to produce novel behaviors and improve position selection in our current generation of AAA RPG titles. In addition, we have expanded UE4’s Environment Query System to serve as a general-purpose utility system; we show how minor modifications allowed the team to use EQS to coordinate combat, reduce behavior tree complexity with a hybrid BT/US approach, and increase character AI quality for a range of tasks such as action and target selection. Attendees will learn how to get the most out of modern spatial query systems with a combination of new techniques and best practices to maximize quality and extend their application to new areas.

Eric Johnson, Square Enix

Eric Johnson is a Senior AI Engineer in the Advanced Technology Division of Square Enix. Before joining the industry in 2008, Eric received a Master’s Degree in Artificial Intelligence from the Georgia Institute of Technology, focusing on case-based reasoning for realtime strategy games. Currently he is working on the AI...

Read full biography »

Eric Johnson, Square Enix

Eric Johnson is a Senior AI Engineer in the Advanced Technology Division of Square Enix. Before joining the industry in 2008, Eric received a Master’s Degree in Artificial Intelligence from the Georgia Institute of Technology, focusing on case-based reasoning for realtime strategy games. Currently he is working on the AI...

Read full biography »

The How and Why of Server Validation for Mobile Simulations

First we will discuss the how and the why of simple mobile simulation game economy, something that you might find in every farming game. Then, we will spice it up with some real time decision making and how it influences the challenge of server validation. We will have a look at how reusing code on server and client, by implementing deterministic simulations, can make our life much easier. We wrap it up with an extreme example where an economy and a battle is based on real time simulations. Expect to see technical details about efficient data serialisation, how to implement deterministic simulations and much more.

Maxim Zaks, Wooga

Maxim Zaks is a freelance Software developer with history in IDE, Web and Mobile development. Last 3.5 years he worked with Wooga/Black Anvil helping them develop mobile strategy games and a small ECS library called Entitas.

Read full biography »

Maxim Zaks, Wooga

Maxim Zaks is a freelance Software developer with history in IDE, Web and Mobile development. Last 3.5 years he worked with Wooga/Black Anvil helping them develop mobile strategy games and a small ECS library called Entitas.

Read full biography »

Integrating Modern AI with no Leaps of Faith: What’s Your Next Step? [Panel]

When you are faced with the challenge of decision making, you may choose among different techniques. Monte Carlo Tree Search, Deep Q Learning, Query Systems or even Evolutionary Algorithms can provide you with different ways of approaching the problem, and each one of them has its own advantages and disadvantages. How do you choose which one fits your problem better? What should you do, and what should you avoid? Can you combine these techniques, or switch from one to another dynamically? Join us at this panel to hear what do our experts think about this and learn from their tips and experiences.

Diego Perez, University of Essex

Diego Perez is a Lecturer in Computer Games and Artificial Intelligence at the University of Essex (UK), where he achieved a PhD in Computer Science (2015). He has published in the domain of Game AI, with research interests on Reinforcement Learning and Evolutionary Computation. He has organized several Game AI...

Read full biography »

Diego Perez, University of Essex

Diego Perez is a Lecturer in Computer Games and Artificial Intelligence at the University of Essex (UK), where he achieved a PhD in Computer Science (2015). He has published in the domain of Game AI, with research interests on Reinforcement Learning and Evolutionary Computation. He has organized several Game AI...

Read full biography »

Online Evolution for Hero Academy and Multi-Action Games

Tree-search algorithms are widely used for decision making in turn-based strategy games. These algorithms do however not perform well for games with millions of possible moves each turn. This talk will explain and show how an evolutionary algorithm, that we call Online Evolution, is used to make a game-playing agent for Hero Academy; a game with around 1 billion possible moves each turn. Online Evolution searches the space of possible action sequences that make up a single turn of the game using a genetic algorithm. This approach looks very promising for this class of game and has been shown to outperform several standard tree-search algorithms.

Niels Justesen, IT University Copenhagen

Niels Justesen holds a B.Sc. in Software Development and just recently finished his M.Sc. in Games Technology at the IT University in Copenhagen. Here he pursued his interests in Game AI and has two peer-reviewed conference publications about game playing algorithms in strategy games. Now he works as a software...

Read full biography »

Niels Justesen, IT University Copenhagen

Niels Justesen holds a B.Sc. in Software Development and just recently finished his M.Sc. in Games Technology at the IT University in Copenhagen. Here he pursued his interests in Game AI and has two peer-reviewed conference publications about game playing algorithms in strategy games. Now he works as a software...

Read full biography »

Computer Go: from Influence Functions to AlphaGo

Computer Go is a game that has been used for many years as a challenge for AI. AlphaGo has received significant press coverage lately, after achieving a victory that surprised many experts in the field. But progress and work within the Go community, pushing the boundaries of research in this game, has been steady over the years before this breakthrough. In this talk, we will review the progress and paradigm shifts from the early days of computer Go to the recent victory of AlphaGo using Deep Learning and Monte Carlo Tree Search, and we will outline possible future directions on this field.

Tristan Cazenave, Université Paris Dauphine

Professor of artificial intelligence at LAMSADE Universite Paris-Dauphine. Author of more than a hundred scientific papers about artificial intelligence in games. He started to publish commercial video games when he was aged 16 and co-founded a successful web agency in 1992.

Read full biography »

Tristan Cazenave, Université Paris Dauphine

Professor of artificial intelligence at LAMSADE Universite Paris-Dauphine. Author of more than a hundred scientific papers about artificial intelligence in games. He started to publish commercial video games when he was aged 16 and co-founded a successful web agency in 1992.

Read full biography »

Hands-On Deep Q-Learning in DOOM [Workshop]

ViZDoom is a Doom-based platform for research in visual learning and visual reinforcement learning, in particular. It allows developing bots that play DOOM using only the raw visual information. In this hands-on workshop, you will have an opportunity to experiment with ViZDoom, learn how to connect it with a deep Q-learning framework, and to train your own vision-only bot in a simple scenario.

Wojciech Jaśkowski, Poznań University of Technology

Wojciech is an Assistant Professor at Poznan University of Technology (Poland), where we achieved a Ph.D. in Computer Science (2011). His has published in the past on combinatorial optimization, genetic programming, test-based problems, reinforcement learning, and coevolution with applications to classic (e.g., Othello, Go) and not-so-classic (Tetris, 2048, Doom) games....

Read full biography »

Wojciech Jaśkowski, Poznań University of Technology

Wojciech is an Assistant Professor at Poznan University of Technology (Poland), where we achieved a Ph.D. in Computer Science (2011). His has published in the past on combinatorial optimization, genetic programming, test-based problems, reinforcement learning, and coevolution with applications to classic (e.g., Othello, Go) and not-so-classic (Tetris, 2048, Doom) games....

Read full biography »

Advances in Deep Reinforcement Learning

The advances in Deep Reinforcement Learning (DRL) allowed recently to obtain highly competent agents for, among others, Atari games and Go. Conveniently from the practical perspective, these methods involve little domain knowledge, being able to learn from raw visual information such as the game board or the screen buffer. After briefly introducing the reinforcement learning problem, the talk will overview the state-of-the-art methods and results in deep reinforcement learning. The final part will be devoted to the recent results in learning to play Doom from raw visual information.

Wojciech Jaśkowski, Poznań University of Technology

Wojciech is an Assistant Professor at Poznan University of Technology (Poland), where we achieved a Ph.D. in Computer Science (2011). His has published in the past on combinatorial optimization, genetic programming, test-based problems, reinforcement learning, and coevolution with applications to classic (e.g., Othello, Go) and not-so-classic (Tetris, 2048, Doom) games....

Read full biography »

Wojciech Jaśkowski, Poznań University of Technology

Wojciech is an Assistant Professor at Poznan University of Technology (Poland), where we achieved a Ph.D. in Computer Science (2011). His has published in the past on combinatorial optimization, genetic programming, test-based problems, reinforcement learning, and coevolution with applications to classic (e.g., Othello, Go) and not-so-classic (Tetris, 2048, Doom) games....

Read full biography »

Speakers & Organizers

Eric Johnson

Maxim Zaks

Diego Perez

Niels Justesen

Tristan Cazenave

Professor of artificial intelligence at LAMSADE Universite Paris-Dauphine. Author of more than a hundred scientific papers about artificial intelligence in games. He started to publish commercial video games when he was aged 16 and co-founded a successful web agency in 1992.

Conference Speaker

Niels Justesen holds a B.Sc. in Software Development and just recently finished his M.Sc. in Games Technology at the IT University in Copenhagen. Here he pursued his interests in Game AI and has two peer-reviewed conference publications about game playing algorithms in strategy games. Now he works as a software developer at IT-Minds building intelligent applications for their clients.

Conference Speaker

Lecturer in Computer Games and AI

Diego Perez is a Lecturer in Computer Games and Artificial Intelligence at the University of Essex (UK), where he achieved a PhD in Computer Science (2015). He has published in the domain of Game AI, with research interests on Reinforcement Learning and Evolutionary Computation. He has organized several Game AI competitions, as the Physical Travelling Salesman Problem and the General Video Game AI competitions, both held in IEEE conferences. He also has programming experience in the videogames industry with titles published for game consoles and PC.

Track Chair and Co-Organizer

Maxim Zaks

Software Developer

Maxim Zaks is a freelance Software developer with history in IDE, Web and Mobile development. Last 3.5 years he worked with Wooga/Black Anvil helping them develop mobile strategy games and a small ECS library called Entitas.

Conference Speaker

Eric Johnson

Senior AI Engineer

Eric Johnson is a Senior AI Engineer in the Advanced Technology Division of Square Enix. Before joining the industry in 2008, Eric received a Master’s Degree in Artificial Intelligence from the Georgia Institute of Technology, focusing on case-based reasoning for realtime strategy games. Currently he is working on the AI for Kingdom Hearts III.

Conference Speaker

Wojciech Jaśkowski

Petra Champandard-Pail

Petra Champandard-Pail

Conference Director & Co-Founder

Petra has a background in business management, and worked as an International Area Manager for a large multi-million dollar corporation. She eventually moved on and joined Alex as the co-founder of AiGameDev.com. Petra is the creative force in the team, and takes care of business!

Assistant Professor

Wojciech is an Assistant Professor at Poznan University of Technology (Poland), where we achieved a Ph.D. in Computer Science (2011). His has published in the past on combinatorial optimization, genetic programming, test-based problems, reinforcement learning, and coevolution with applications to classic (e.g., Othello, Go) and not-so-classic (Tetris, 2048, Doom) games. As his current interests concentrate on Vision-based Deep Reinforcement Learning, recently he led a team that developed ViZDoom - a reinforcement learning research platform that allows creating bots that play Doom using only the screen buffer. He is also a winner of several AI or game-oriented competitions such as Hello World Open 2014, Google ROADEF/EURO Challenge 2012 (junior category), or Microsoft ImagineCup Hoshimi Project 2005

Conference Speaker

Browse Conference Tracks

Analytics & Data Science

Agent Behavior & Coordination

Character Animation

Cognition, Bots & Understanding

Dynamic Dialog & Storytelling

Generative Systems & Design

Human Interaction & Recognition

Procedural Content Generation

Real-time Decisions