Deep Reinforcement Learning for High Level Character Control

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.

References in corpus (8)

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• Generative Adversarial Imitation Learning
• Character Controllers Using Motion VAEs
• Learning Symmetric and Low-energy Locomotion
• Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation
• Hierarchical visuomotor control of humanoids
• CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion
• Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks