Premium
LEARNING AND VERIFYING SAFETY CONSTRAINTS FOR PLANNERS IN A KNOWLEDGE‐IMPOVERISHED SYSTEM
Author(s) -
Levine Geoffrey,
Kuter Ugur,
Rebguns Antons,
Green Derek,
Spears Diana
Publication year - 2012
Publication title -
computational intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.353
H-Index - 52
eISSN - 1467-8640
pISSN - 0824-7935
DOI - 10.1111/j.1467-8640.2012.00416.x
Subject(s) - computer science , domain (mathematical analysis) , plan (archaeology) , benchmark (surveying) , artificial intelligence , machine learning , constraint (computer aided design) , trace (psycholinguistics) , bayesian network , software engineering , engineering , mechanical engineering , mathematical analysis , linguistics , philosophy , mathematics , archaeology , geodesy , history , geography
We present a Bayesian approach to learning flexible safety constraints and subsequently verifying whether plans satisfy these constraints. Our approach, called the Safety Constraint Learner/Checker (SCLC) , infers safety constraints from a single expert demonstration trace and minimal background knowledge, and applies these constraints to the solutions proposed by multiple planning agents in an integrated and heterogeneous ensemble. The SCLC calculates how much to blame plan fragments (partial solutions) generated by the individual planning agents. This information is used when composing these fragments into a final overall plan. In particular, fragments whose safety violations exceed a threshold are rejected. This facilitates the generation of safe plans. We have integrated the SCLC within the Generalized Integrated Learning Architecture , which was designed for Defense Advanced Research Projects Agency (DARPA)’s Integrated Learning (IL) program. The main goal of the IL program is to promote the development and success of sophisticated systems that learn to solve challenging real‐world problems based on a simple demonstration by a human expert and exiguous domain knowledge. We present experimental results showing the advantages of the SCLC on two multiagent problem‐solving tasks that were benchmark applications in DARPA’s IL program.