CHILD: A First Step Towards Continual Learning

Authors:
Mark B. Ring
Affiliations:
Adaptive Systems Research Group, GMD–German National Research Center for Information Technology, Schloß Birlinghoven, D-53 754 Sankt Augustin, Germany. E-mail: Mark.Ring@gmd.de
Venue:
Machine Learning - Special issue on inductive transfer
Year:
1997

Citing 13
Cited 6

Made-up minds: a constructivist approach to artificial intelligence

Made-up minds: a constructivist approach to artificial intelligence
Cognitive action theory as a control architecture

Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
The recurrent cascade-correlation architecture

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
The Induction of Dynamical Recognizers

Machine Learning - Connectionist approaches to language learning
Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching

Machine Learning
Transfer of Learning by Composing Solutions of Elemental Sequential Tasks

Machine Learning
Planning simple trajectories using neural subgoal generators

Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Continual learning in reinforcement environments

Continual learning in reinforcement environments
Chunking in Soar: The Anatomy of a General Learning Mechanism

Machine Learning
Learning Sequential Tasks by Incrementally Adding Higher Orders

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Discriminability-Based Transfer between Neural Networks

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Feudal Reinforcement Learning

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Constructive learning of recurrent neural networks: limitations of recurrent cascade correlation and a simple solution

IEEE Transactions on Neural Networks

Strategies for lifelong knowledge extraction from the web

Proceedings of the 4th international conference on Knowledge capture
Learning to count by think aloud imitation

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Short term memories and forcing the re-use of knowledge for generalization

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Machine lifelong learning: challenges and benefits for artificial general intelligence

AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Inconsistency-Induced Learning for Perpetual Learners

International Journal of Software Science and Computational Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Continual learning is the constant developmentof increasingly complex behaviors; the process of building morecomplicated skills on top of those already developed. Acontinual-learning agent should therefore learn incrementally andhierarchically. This paper describes CHILD, an agent capable of Continual, Hierarchical, Incremental Learning and Development. CHILD can quickly solve complicated non-Markovian reinforcement-learning tasks and can then transfer its skills tosimilar but even more complicated tasks, learning these faster still.