Deep Reinforcement Learning for High Level Character Control

TL;DR

This paper combines traditional animation, heuristic methods, and reinforcement learning to create intelligent, high-level character controllers in 3D environments, focusing on environment design and generalization.

Contribution

It introduces a framework integrating artistic control with reinforcement learning for character behavior, emphasizing environment construction and analysis for improved learning.

Findings

Environment design significantly impacts learning outcomes.

Reinforcement learning enables generalization of behaviors.

Analysis provides guidelines for developing learning environments.

Abstract

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.