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.

Use the GDC 2021 Session Viewer to browse and sort the ever-growing list of sessions by day, time, pass type, topic, and format. All registered attendees will be able to build their personal schedule directly within the event platform, once live early July 2021. All times are listed in Pacific Time.

AI Summit: Beyond Pre-training: Experiences of Applying Imitation Learning in Game AI

Wang Meng  (Senior Deep Learning Researcher, Netease)

Date: Monday, July 19

Time: 2:40pm - 3:10pm

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Session

Vault Recording: Video

Audience Level: N/A: I prefer to present live on-site but I am open to delivering a virtual presentation

Traditionally, imitation learning is used as a technique to train AI from player data or pre-train an AI for further learning algorithms such as reinforcement learning. This session will introduce some interesting applications of imitation learning tried in the Netease game, including the traditional way of using imitation learning to directly train an AI or using imitation learning to accelerate the training of reinforcement learning AI, as well as some new attempts such as using imitation learning to train multi-style AIs or improving the reinforcement learning AI to be more human-like.

Takeaway

The attendee can learn some interesting imitation learning applications in the game besides simply training an AI with player data.

Intended Audience

The audience who are interested in game AI and imitation learning.