Boosted curriculum reinforcement learning

P Klink, C D'Eramo, J Peters… - … Conference on Learning …, 2021 - openreview.net
Curriculum value-based reinforcement learning (RL) solves a complex target task by reusing
action-values across a tailored sequence of related tasks of increasing difficulty. However …

Learning to learn with active adaptive perception

DM Bossens, NC Townsend, AJ Sobey - Neural networks, 2019 - Elsevier
Increasingly, autonomous agents will be required to operate on long-term missions. This will
create a demand for general intelligence because feedback from a human operator may be …

Global versus local constructive function approximation for on-line reinforcement learning

P Vamplew, R Ollington - Australasian Joint Conference on Artificial …, 2005 - Springer
In order to scale to large state-spaces, reinforcement learning (RL) algorithms need to apply
function approximation techniques. Research on function approximation for RL has so far …

The Logic of Adaptive Behavior-Knowledge Representation and Algorithms for the Markov Decision Process Framework in First-Order Domains

M Van Otterlo - 2008 - research.utwente.nl
Learning and reasoning in large, structured, probabilistic worlds is at the heart of artificial
intelligence. Markov decision processes have become the de facto standard in modeling …

Dynamic network architectures for deep q-learning: Modelling neurogenesis in artificial intelligence

P Eriksson, L Westlund Gotby - 2019 - odr.chalmers.se
Artificial neural networks have become popular within a range of machine learning fields for
their ability to solve complex problems, with one of the uses as function approximators in Q …

[PDF][PDF] Reinforcement learning with limited prior knowledge in long-term environments

D Bossens - 2020 - drive.google.com
It has been estimated that by 2030 global GDP could increase by 13.8% merely due to the
impact of Artificial Intelligence (AI). AI has become an instrumental part of nearly all human …

Towards the Learning Behaviour and Performance of Artificial Neural Networks in Production Control

B Scholz-Reiter, F Harjes - … LDIC 2012 Bremen, Germany, February/March …, 2013 - Springer
Recently, artificial neural networks have proven their potential in manifold production related
tasks. At this, the learning ability is both their greatest strength and greatest weakness. The …

Towards the Learning Behaviour

B Scholz-Reiter, F Harjes - Dynamics in Logistics: Third …, 2013 - books.google.com
Recently, artificial neural networks have proven their potential in manifold production related
tasks. At this, the learning ability is both their greatest strength and greatest weakness. The …

[PDF][PDF] THE LOGIC OF ADAPTIVE BEHAVIOR

ASD MAKING, UIN FIRST-ORDER - 2008 - martijnvanotterlo.nl
One of my favorite stories is The Library of Babel (1941) by the Argentinean writer and
librarian Jorge Luis Borges (1899–1986). In this fantastic story, Borges describes an …