Modular problem decomposition is often employed to cope with complex real-world problems. An intelligent decomposition can eeciently lead to compact and general solutions but is, in most cases, the result of laborious domain analysis and engineering. Little has been done to automatically discover natural decompositions of complex problems while simultaneously solving the sub-problems; usually, a decomposition architecture must be speciied in advance. This paper presents the Evolutionary Speciation Genetic Programming (ESGP) framework which evolves a problem decomposition as an ensemble of species whose members collectively solve the problem. Problem decomposition emerges as a result of speci-ation and specialization within each species. Spe-ciation is facilitated by the symbiotic representation of individuals. Cooperation among species emerges through coevolution. We present experiments on complex, multi-regime function approximation problems to demonstrate and analyze the basic concepts of the ESGP framework.

Abstract: A real-time motion engine for interactive synthetic characters, either virtual or physical,needs to allow expressivity and interactivity of motion in order to maintain the illusion oflife. Canned animation examples from an animator or motion capture device are expressive,but not very interactive, often leading to repetition. Conversely, numerical proceduraltechniques such as Inverse Kinematics (IK) tend to be very interactive, but often appear"robotic" and require parameter tweaking by...

The ability to learn is a potentially compelling and important quality for interactive synthetic characters. To that end, we describe a practical approach to real-time learning for synthetic characters. Our implementation is grounded in the techniques of reinforcement learning and informed by insights from animal training. It 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.We built an autonomous animated dog that can be trained with a technique used to train real dogs called "clicker training". Capabilities demonstrated include being trained to recognize and use acoustic patterns as cues for actions, as well as to synthesize new actions from novel paths through its motion space.A key contribution of this paper is to demonstrate that by addressing the three problems of state, action, and state-action space discovery at the same time, the solution for each becomes easier. Finally, we articulate heuristics and design principles that make learning practical for synthetic characters.