Evolution and learning in an intrinsically motivated reinforcement learning robot

Authors:
Massimiliano Schembri;Marco Mirolli;Gianluca Baldassarre
Affiliations:
Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche, Roma, Italy;Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche, Roma, Italy;Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche, Roma, Italy
Venue:
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Year:
2007

Citing 7
Cited 4

A possibility for implementing curiosity and boredom in model-building neural controllers

Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning

Artificial Intelligence
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Learning and Evolution

Autonomous Robots
Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments

Evolutionary Computation
Intrinsic Motivation Systems for Autonomous Mental Development

IEEE Transactions on Evolutionary Computation
A modular neural-network model of the basal ganglia's role in learning and selecting motor behaviours

Cognitive Systems Research

Review: learning like a baby: A survey of artificial intelligence approaches

The Knowledge Engineering Review
Active learning of inverse models with intrinsically motivated goal exploration in robots

Robotics and Autonomous Systems
Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: A simulated robotic study

Neural Networks
2013 Special Issue: Intrinsically motivated action-outcome learning and goal-based action recall: A system-level bio-constrained computational model

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Studying the role played by evolution and learning in adaptive behavior is a very important topic in artificial life research. This paper investigates the interplay between learning and evolution when agents have to solve several different tasks, as it is the case for real organisms but typically not for artificial agents. Recently, an important thread of research in machine learning and developmental robotics has begun to investigate how agents can solve different tasks by composing general skills acquired on the basis of internal motivations. This work presents a hierarchical, neural-network, actor-critic architecture designed for implementing this kind of intrinsically motivated reinforcement learning in real robots. We compare the results of several experiments in which the various components of the architecture are either trained during lifetime or evolved through a genetic algorithm. The most important results show that systems using both evolution and learning outperform systems using either one of the two, and that, among the former, systems evolving internal reinforcers for learning building-block skills have a higher evolvability than those directly evolving the related behaviors.