Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives

by   Christian Gumbsch, et al.

Voluntary behavior of humans appears to be composed of small, elementary building blocks or behavioral primitives. While this modular organization seems crucial for the learning of complex motor skills and the flexible adaption of behavior to new circumstances, the problem of learning meaningful, compositional abstractions from sensorimotor experiences remains an open challenge. Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures (SUBMODES), that explores behavior and identifies the underlying behavioral units completely from scratch. The SUBMODES architecture bootstraps sensorimotor exploration using a self-organizing neural controller. While exploring the behavioral capabilities of its own body, the system learns modular structures that predict the sensorimotor dynamics and generate the associated behavior. In line with recent theories of event perception, the system uses unexpected prediction error signals, i.e., surprise, to detect transitions between successive behavioral primitives. We show that, when applied to two robotic systems with completely different body kinematics, the system manages to learn a variety of complex and realistic behavioral primitives. Moreover, after initial self-exploration the system can use its learned predictive models progressively more effectively for invoking model predictive planning and goal-directed control in different tasks and environments.


page 4

page 7

page 9


Inference of Affordances and Active Motor Control in Simulated Agents

Flexible, goal-directed behavior is a fundamental aspect of human life. ...

Efficient Learning of High Level Plans from Play

Real-world robotic manipulation tasks remain an elusive challenge, since...

Autonomous learning and chaining of motor primitives using the Free Energy Principle

In this article, we apply the Free-Energy Principle to the question of m...

Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture

We introduce a dynamic artificial neural network-based (ANN) adaptive in...

Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots

We introduce the Self-Adaptive Goal Generation - Robust Intelligent Adap...

Developing hierarchical anticipations via neural network-based event segmentation

Humans can make predictions on various time scales and hierarchical leve...

Active World Model Learning with Progress Curiosity

World models are self-supervised predictive models of how the world evol...

Please sign up or login with your details

Forgot password? Click here to reset