Use the GDC 2021 Session Viewer to browse and sort the ever-growing list of sessions by pass type, topic, and format. You will be able to build your personal schedule directly within the event platform, once live early July 2021.
Richard Wu (Software Engineer, Google)
Ji Hun Kim (Software Engineer, Google)
Andeep Toor (Software Engineer, Google)
Trung Le (Software Engineer, Google)
Pass Type: All Access Pass, Summits Pass
Vault Recording: TBD
Audience Level: N/A: I prefer to present live on-site but I am open to delivering a virtual presentation
What can machine learning do? Join Stadia's R&D team in a journey to integrate machine learning into every part of the game development pipeline through an experiment called Project Chimera. We will cover two main topics: 1) ML for content amplification: how we used conditional generative adversarial networks layered with artistic style transfer to create a new image creation pipeline guided by our artists; 2) ML for balancing: how we used reinforcement learning as a system design partner to identify exploits and suggest tuning for the game state machine;.
Learn and be inspired by some ideas about how machine learning can be used to accelerate and enrich game development.
Game developers curious about the future of machine learning for games will find this talk approachable and entertaining. We'll share details about what worked, what didn't, what we'd do differently, and what excites us about the future of this applied research.