Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context

TL;DR

This paper proposes a computational model inspired by cognitive science theories to enable robots to autonomously develop internal world models for better adaptation and skill learning, demonstrated through simulation experiments.

Contribution

It introduces a novel model combining sensorimotor contingencies and predictive processing theories to facilitate autonomous world model acquisition in robots.

Findings

The model successfully learns latent states in simulations.

It enhances the robot's ability to adapt to new situations.

The approach offers a pathway for more autonomous skill acquisition.

Abstract

Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning. However current computational reinforcement learning agents mostly learn each individual skill entirely from scratch. How can we enable artificial agents, such as robots, to acquire some form of generic knowledge, which they could leverage for the learning of new skills? This paper argues that, like the brain, the cognitive system of artificial agents has to develop a world model to support adaptive behavior and learning. Inspiration is taken from two recent developments in the cognitive science literature: predictive processing theories of cognition, and the sensorimotor contingencies theory of perception. Based on these, a hypothesis is formulated about what the content of information might be that is encoded in an internal world model, and how an agent could autonomously acquire it. A computational model is described to formalize this hypothesis, and is evaluated in a series of simulation experiments.