Learning measures of progress for planning domains

Authors:
SungWook Yoon;Alan Fern;Robert Givan
Affiliations:
Electrical & Computer Engineering, Purdue University, West Lafayette, IN;Computer Science Department, Oregon State University, Corvallis, OR;Electrical & Computer Engineering, Purdue University, West Lafayette, IN
Venue:
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Year:
2005

Citing 10
Cited 6

Learning to fly

ML92 Proceedings of the ninth international workshop on Machine learning
Taxonomic syntax for first order inference

Journal of the ACM (JACM)
Learning action strategies for planning domains

Artificial Intelligence
Learning Decision Lists

Machine Learning
Learning Declarative Control Rules for Constraint-BAsed Planning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
A logical measure of progress for planning

Eighteenth national conference on Artificial intelligence
Learning to fly by combining reinforcement learning with behavioural cloning

ICML '04 Proceedings of the twenty-first international conference on Machine learning
The FF planning system: fast plan generation through heuristic search

Journal of Artificial Intelligence Research
Learning to take actions

AAAI'96 Proceedings of the thirteenth national 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

Learning Control Knowledge for Forward Search Planning

The Journal of Machine Learning Research
Practical solution techniques for first-order MDPs

Artificial Intelligence
The first probabilistic track of the international planning competition

Journal of Artificial Intelligence Research
Discriminative learning of beam-search heuristics for planning

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Using learned policies in heuristic-search planning

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
RECYCLE: Learning looping workflows from annotated traces

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study an approach to learning heuristics for planning domains from example solutions. There has been little work on learning heuristics for the types of domains used in deterministic and stochastic planning competitions. Perhaps one reason for this is the challenge of providing a compact heuristic language that facilitates learning. Here we introduce a new representation for heuristics based on lists of set expressions described using taxonomic syntax. Next, we review the idea of a measure of progress (parmar 2002), which is any heuristic that is guaranteed to be improvable at every state. We take finding a measure of progress as our learning goal, and describe a simple learning algorithm for this purpose. We evaluate our approach across a range of deterministic and stochastic planning-competition domains. The results show that often greedily following the learned heuristic is highly effective. We also show our heuristic can be combined with learned rule-based policies, producing still stronger results.