Unique state and automatical action abstracting based on logical MDPs with negation

Authors:
Song Zhiwei;Chen Xiaoping
Affiliations:
Computer Science Department, University of Science and Technology of China, Hefei, Anhui, China;Computer Science Department, University of Science and Technology of China, Hefei, Anhui, China
Venue:
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part II
Year:
2006

Citing 9
Cited 0

Blocks World revisited

Artificial Intelligence
Relational reinforcement learning

Machine Learning - Special issue on inducive logic programming
Foundations of Inductive Logic Programming

Foundations of Inductive Logic Programming
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Bellman goes relational

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Generalizing plans to new environments in relational MDPs

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Symbolic dynamic programming for first-order MDPs

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Inductive policy selection for first-order MDPs

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we introduce negation into Logical Markov Decision Processes, which is a model of Relational Reinforcement Learning. In the new model nLMDP the abstract state space can be constructed in a simple way, so that a good property of complementarity holds. Prototype action is also introduced into the model. A distinct feature of the model is that applicable abstract actions can be obtained automatically with valid substitutions. Given a complementary abstract state space and a set of prototype actions, a model-free Θ-learing method is implemented for evaluating the state-action-substitution value funcion.