Learning to Take Actions

Authors:
Roni Khardon
Affiliations:
Division of Informatics, University of Edinburgh, JCMB, King‘s Buildings, Edinburgh EH9 3JZ, Scotland. roni@dcs.ed.ac.uk
Venue:
Machine Learning
Year:
1999

Citing 59
Cited 18

A theory of the learnable

Communications of the ACM
Macro-operators: a weak method for learning

Artificial Intelligence - Lecture notes in computer science 178
Learning one subprocedure per lesson

Artificial Intelligence
Production system models of learning and development

Production system models of learning and development
Occam's razor

Information Processing Letters
Learning regular sets from queries and counterexamples

Information and Computation
Computational limitations on learning from examples

Journal of the ACM (JACM)
Universal planning: an (almost) universally bad idea

AI Magazine
Penguins can make cake

AI Magazine
In defense of reaction plans as caches

AI Magazine
Classifier systems and genetic algorithms

Artificial Intelligence
Quantitative results concerning the utility of explanation-based learning

Artificial Intelligence
Acquiring Recursive and Iterative Concepts with Explanation-Based Learning

Machine Learning
Unified theories of cognition

Unified theories of cognition
On learning from exercises

COLT '89 Proceedings of the second annual workshop on Computational learning theory
Integrated architecture for learning, planning, and reacting based on approximating dynamic programming

Proceedings of the seventh international conference (1990) on Machine learning
Intelligence without representation

Artificial Intelligence
PAC-learnability of determinate logic programs

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Technical Note: \cal Q-Learning

Machine Learning
Learning to fly

ML92 Proceedings of the ninth international workshop on Machine learning
Temporal difference learning of backgammon strategy

ML92 Proceedings of the ninth international workshop on Machine learning
Learning in embedded systems

Learning in embedded systems
Mining association rules between sets of items in large databases

SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Learning by analogical reasoning in general problem-solving

Learning by analogical reasoning in general problem-solving
Efficient reinforcement learning

COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Inductive logic programming: derivations, successes and shortcomings

ACM SIGART Bulletin
Efficient distribution-free learning of probabilistic concepts

Journal of Computer and System Sciences - Special issue: 31st IEEE conference on foundations of computer science, Oct. 22–24, 1990
The computational complexity of propositional STRIPS planning

Artificial Intelligence
First-order jk-clausal theories are PAC-learnable

Artificial Intelligence
Circuits of the mind

Circuits of the mind
Inducing deterministic Prolog parsers from treebanks: a machine learning approach

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
An introduction to computational learning theory

An introduction to computational learning theory
A comparative analysis of partial order planning and task reduction planning

ACM SIGART Bulletin
Temporal difference learning and TD-Gammon

Communications of the ACM
Rationality

COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Learning to reason with a restricted view

COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Learning to reason

Journal of the ACM (JACM)
The Architecture of Cognition

The Architecture of Cognition
Soar Papers: Research on Integrated Intelligence

Soar Papers: Research on Integrated Intelligence
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Learning Logical Definitions from Relations

Machine Learning
Learning Conjunctive Concepts in Structural Domains

Machine Learning
Learning Sequential Decision Rules Using Simulation Models and Competition

Machine Learning - Special issue on genetic algorithms
Learning Decision Lists

Machine Learning
Learning to Predict by the Methods of Temporal Differences

Machine Learning
Chunking in Soar: The Anatomy of a General Learning Mechanism

Machine Learning
Explanation-Based Generalization: A Unifying View

Machine Learning
Explanation-Based Learning: An Alternative View

Machine Learning
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
The complexity of theorem-proving procedures

STOC '71 Proceedings of the third annual ACM symposium on Theory of computing
Human Problem Solving

Human Problem Solving
Induction of first-order decision lists: results on learning the past tense of English verbs

Journal of Artificial Intelligence Research
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
A formal framework for speedup learning from problems and solutions

Journal of Artificial Intelligence Research
Pac-learning recursive logic programs: efficient algorithms

Journal of Artificial Intelligence Research
Extending classical planning to real-world execution with machine learning

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Learning to reason the non monotonic case

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
On the size of reactive plans

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Linear time near-optimal planning in the blocks world

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2

Learning Function-Free Horn Expressions

Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Learning cost-sensitive active classifiers

Artificial Intelligence
Learning strategies for story comprehension: a reinforcement learning approach

ICML '05 Proceedings of the 22nd international conference on Machine learning
Relating reinforcement learning performance to classification performance

ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning goal hierarchies from structured observations and expert annotations

Machine Learning
Learning Recursive Theories in the Normal ILP Setting

Fundamenta Informaticae
Introducing possibilistic logic in ILP for dealing with exceptions

Artificial Intelligence
Learning to assign degrees of belief in relational domains

Machine Learning
Practical solution techniques for first-order MDPs

Artificial Intelligence
Approximate policy iteration with a policy language bias: solving relational Markov decision processes

Journal of Artificial Intelligence Research
Learning strategies for open-domain natural language question answering

ACLstudent '05 Proceedings of the ACL Student Research Workshop
Learning strategies for open-domain natural language question answering

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Inductive logic programming algorithm for estimating quality of partial plans

MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
Learning action descriptions of opponent behaviour in the robocup 2D simulation environment

ILP'10 Proceedings of the 20th international conference on Inductive logic programming
Acquisition of hierarchical reactive skills in a unified cognitive architecture

Cognitive Systems Research
Learning Recursive Theories in the Normal ILP Setting

Fundamenta Informaticae
Learning policies for battery usage optimization in electric vehicles

ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part II
Learning policies for battery usage optimization in electric vehicles

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We formalize a model for supervised learning ofaction strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. We then identify a class of rule-based action strategies for which polynomial time learning is possible. The representation of strategies is a generalization of decision lists;strategies include rules with existentially quantified conditions,simple recursive predicates, and small internal state,but are syntactically restricted.We also study the learnability of hierarchically composed strategies wherea subroutine already acquired can be used as a basic action in a higherlevel strategy. We prove some positive results in this setting,but also show that in some cases the hierarchical learning problem is computationally hard.