Board-Laying Techniques Improve Local Search in Mixed Planning and Scheduling

When searching the space of possible plans for combined planning and scheduling problems we often reach a local maximum and must either backtrack or otherwise modify the plan to make further progress. Occasionally, we can make large steps in the search space by aggregating constraints. Our techniques improve the performance of our planner/scheduler on real problems.

• Type: Conference
• Year: 2000
• Where: ECAIW
• Authors: Russell Knight, Gregg Rabideau, Steve A. Chien
• Keywords: ECAIW 2000, Intelligent Agents, Local Maximum, Possible Plans, Scheduling Problems