Session Name: | AI Summit: Beyond Pre-training: Experiences of Applying Imitation Learning in Game AI |
Speaker(s): | Meng Wang |
Company Name(s): | Netease |
Track / Format: | AI Summit |
Did you know free users get access to 30% of content from the last 2 years?
Overview: | 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. |