Learning Probabilistic Relational Planning Rules

13 years 11 months ago

Download people.csail.mit.edu

To learn to behave in highly complex domains, agents must represent and learn compact models of the world dynamics. In this paper, we present an algorithm for learning probabilistic STRIPS-like planning operators from examples. We demonstrate the effective learning of rule-based operators for a wide range of traditional planning domains.

Hanna Pasula, Luke S. Zettlemoyer, Leslie Pack Kae

Real-time Traffic

Artificial Intelligence | Complex Domains | KR 2004 | STRIPS-like Planning Operators | Traditional Planning Domains |

claim paper

» Planning with Noisy Probabilistic Relational Rules

» Approximate inference for planning in stochastic relational worlds

» Probabilistic Backward and Forward Reasoning in Stochastic Relational Worlds

» Learning Parameters for Relational Probabilistic Models with NoisyOr Combining Rule

» Learning Symbolic Models of Stochastic Domains

» Discovering Relational Domain Features for Probabilistic Planning

» Rule value reinforcement learning for cognitive agents

» Learning SituationDependent Costs Improving Planning from Probabilistic Robot Execution

Post Info
More Details (n/a)

Added	02 Jul 2010
Updated	02 Jul 2010
Type	Conference
Year	2004
Where	KR
Authors	Hanna Pasula, Luke S. Zettlemoyer, Leslie Pack Kaelbling

Comments (0)

Sciweavers

Learning Probabilistic Relational Planning Rules

Artificial Intelligence | Complex Domains | KR 2004 | STRIPS-like Planning Operators | Traditional Planning Domains |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers