GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of GDC sessions by time, pass type, topic, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live.

If you've registered for GDC, you can use the same login credentials for your Session Scheduler account. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.

AI Summit: Imitation Learning: Building Practical Agents to Test and Explore a First-Person Shooter

Igor Borovikov (Sr. AI Scientist, EA)

Location: Room 2002, West Hall

Date: Monday, March 16

Time: 3:50pm - 4:20pm

Pass Type: All Access Pass, Core+Summits Pass, Summits Pass - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: Intermediate

The talk introduces style-centric autoplay agents that game developers can train quickly and on a budget to facilitate testing and evaluating the gameplay of a title under development. The focus on the practical and stylistic aspects suggests a simple approach based on the Markov model. Markov agents are trainable interactively and can incorporate new game features without re-training the entire model. While such agents efficiently capture the demonstrated gameplay style, they may require fallback heuristics to address possible lack of performance, or the game states not explicitly present in organic play-throughs. Imitation learning on the data bootstrapped from the enhanced with heuristics Markov agent allows training of a compact computationally efficient DNN model suitable for automated game evaluation and testing. A generic First-Person Shooter game example provides a practical context for the presentation. The GitHub repository illustrates Markov agents in more detail and uses OpenAI gym environments for an interactive demo.

Takeaway

The attendees will get an insight into a simple yet effective approach to creating autoplay agents for game testing and evaluation during its development.

Intended Audience

The target audience is moderately experienced AI game developers with the basic knowledge of Markov processes, basic concepts of Imitation and Reinforcement Learning, Deep Neural Nets, interested in creating their autoplay bots for game testing and balancing.