Learn More
We define a measure of redundant information based on projections in the space of probability distributions. Redundant information between random variables is information that is shared between those variables. But, in contrast to mutual information, redundant information denotes information that is shared about the outcome of a third variable. Formalizing(More)
Sensor evolution in nature aims at improving the acquisition of information from the environment and is intimately related with selection pressure toward adaptivity and robustness. Our work in the area indicates that information theory can be applied to the perception-action loop. This letter studies the perception-action loop of agents, which is modeled as(More)
This article describes a developmental system based on information theory implemented on a real robot that learns a model of its own sensory and actuator apparatus. There is no innate knowledge regarding the modalities or representation of the sensory input and the actuators, and the system relies on generic properties of the robot's world such as piecewise(More)
The classical approach to using utility functions suffers from the drawback of having to design and tweak the functions on a case by case basis. Inspired by examples from the animal kingdom, social sciences and games we propose empowerment, a rather universal function, defined as the information-theoretic capacity of an agent's actuation channel. The(More)
The central resource processed by the sensorimotor system of an organism is information. We propose an information-based quantity that allows one to characterize the efficiency of the perception-action loop of an abstract organism model. It measures the potential of the organism to imprint information on the environment via its actuators in a way that can(More)
We critically examine a model that attempts to explain emergence of power laws (e.g., Zipf's law) in human language. The model is based on the principle of least effort in communications — specifically, the overall effort is balanced between the speaker effort and listener effort, with some trade-off. It has been shown that an information-theoretic(More)
We apply kernel-based methods to solve the difficult reinforcement learning problem of 3vs2 keepaway in RoboCup simulated soccer. Key challenges in keepaway are the high-dimensionality of the state space (rendering conventional discretization-based function approximation like tilecoding infeasible), the stochasticity due to noise and multiple learning(More)
In this paper we focus on the problem of making a model of the sensory apparatus from raw uninterpreted sensory data as defined by Pierce and Kuipers (Artificial Intelligence 92:169-227, 1997). The method relies on generic properties of the agent's world such as piecewise smooth effects of movement on sensory features. We extend a previously described(More)