Search

Now showing items 21-30 of 34

Faster Learning in Embodied Systems through Characteristic Attitudes

Jacob, D.; Polani, D.; Nehaniv, C.L. (IEEE, 2005)

The degree of potential damage in agonistic contests and its effects on social aggression, territoriality and display evolution

Lowe, R.; Nehaniv, C.L.; Polani, D.; Cañamero, Lola (IEEE, 2005)

The potential for animals to inflict damage on one another whilst competing for indivisible resources is a factor of crucial importance when determining pay-offs to such animals and consequent likelihood of adopting an ...

From Unknown Sensors and Actuators to Visually Guided Movement

Olsson, L.; Nehaniv, C.L.; Polani, D. (2005)

This paper describes a developmental system implemented on a real robot that learns a model of its own sensory and actuator apparatuses. There is no innate knowledge regarding the modality or representation of the sensoric ...

Legs that can walk: Embodiment-Based Modular Reinforcement Learning applied

Jacob, D.; Polani, D.; Nehaniv, C.L. (IEEE, 2005)

Experiments to illustrate a novel methodology for reinforcement learning in embodied physical agents are described. A simulated legged robot is decomposed into structurebased modules following the authors' EMBER principles ...

All Else Being Equal Be Empowered

Klyubin, A.S.; Polani, D.; Nehaniv, C.L. (2005)

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 ...

Discovering Motion Flow by Temporal-Informational Correlations in Sensors

Olsson, L.; Nehaniv, C.L.; Polani, D. (2005)

Inferring dependencies in Embodiment-based modular reinforcement learning

Jacob, D.; Polani, D.; Nehaniv, C.L. (2005)

The state-spaces needed to describe realistic--physical embodied agents are extremely large, which presents a serious challenge to classical einforcement learning schemes. In previous work--(Jacob et al., 2005a, Jacob et ...

Empowerment: a universal agent-centric measure of control

Klyubin, A.S.; Polani, D.; Nehaniv, C.L. (2005)

Improving Learning for Embodied Agents in Dynamic--Environments by State Factorisation

Jacob, D.; Polani, D.; Nehaniv, C.L. (2004)

A new reinforcement learning algorithm designed--specifically for robots and embodied systems--is described. Conventional reinforcement learning methods intended for learning general tasks suffer from a number of disadvantages ...

Information Trade-Offs and the Evolution of Sensory Layout

Olsson, L.; Nehaniv, C.L.; Polani, D. (2004)

In nature, sensors evolve to capture relevant information needed for organisms of a particular species to survive and reproduce. In this paper we study how sensor layouts may evolve in different environments and under ...