Deep Reinforcement Learning for High Level Character Control
This addresses the challenge of achieving artistic control and generalization in character animation for media applications, but it is incremental as it builds on existing methods.
The paper tackles the problem of creating intelligent characters for computational media by combining traditional animations, heuristic behavior, and reinforcement learning, resulting in a dog character that learns high-level behaviors like fetching in a 3D environment, with analysis providing insights into environment design and generalization.
In this paper, we propose the use of traditional animations, heuristic behavior and reinforcement learning in the creation of intelligent characters for computational media. The traditional animation and heuristic gives artistic control over the behavior while the reinforcement learning adds generalization. The use case presented is a dog character with a high-level controller in a 3D environment which is built around the desired behaviors to be learned, such as fetching an item. As the development of the environment is the key for learning, further analysis is conducted of how to build those learning environments, the effects of environment and agent modeling choices, training procedures and generalization of the learned behavior. This analysis builds insight of the aforementioned factors and may serve as guide in the development of environments in general.