Abstract: A practical approach to real-time learning for synthetic characters grounded in the techniques of reinforcement learning and informed by insights from animal training. The approach simplifies the learning task for characters by (a) enabling them to take advantage of predictable regularities in their world, (b) allowing them to make maximal use of any supervisory signals, and (c) making them easy to train by humans. An autonomous animated dog is described that can be trained with a technique used to train real dogs called “clicker training.

Abstract: A three dimensional physical toy that can be manipulated by a user is connected to a computer. Interchangeable accessory parts can be plugged into the toy via mechanisms which identify the accessory parts immediately when they are plugged into the toy body. A software program running in the computer displays a graphical character representation of the toy, including the accessory parts that have been plugged into the toy in a virtual environment on a monitor screen. The toy and the accessory parts interact dynamically with the software program so that the graphical character representation of the toy appears on the screen exactly as it physically appears to the user. The toy interacts with the virtual environment in each stage of construction an as each accessory part is added or removed. Therefore, as various accessory parts are inserted into, or removed from, the toy, the graphical character representation of the toy interacts with the virtual environment in different ways.

Abstract: An electronic system for integrating a user's moving image into a computer-generated pictorial environment, and allowing the user to interact with the environment and objects therein. The environment is rendered on a screen display in a manner that simulates three dimensions, including respect for occlusion relationships among the user and objects in the environment. The resulting image, which changes as the user gestures and interacts with the environment, is projected onto a large screen that the user faces. The environment includes a series of mobile entities, or "agents," which respond to one or more of the user's changing position, gestures and voice, exhibiting context-dependent behavior that appears semi-intelligent.