Improving Search by Utilizing State Information in OPTIC Planners Compilation to LP
This work addresses efficiency issues in automated planning for real-life applications, representing an incremental improvement in domain-specific optimization.
The paper tackles the computational cost of linear programming (LP) checks in OPTIC planners by proposing a method to use state-specific information for better solver selection and faster solving, demonstrating significant performance improvements across six domains.
Automated planners are computer tools that allow autonomous agents to make strategies and decisions by determining a set of actions for the agent that to take, which will carry a system from a given initial state to the desired goal state. Many planners are domain-independent, allowing their deployment in a variety of domains. Such is the broad family of OPTIC planners. These planners perform Forward Search and call a Linear Programming (LP) solver multiple times at every state to check for consistency and to set bounds on the numeric variables. These checks can be computationally costly, especially in real-life applications. This paper suggests a method for identifying information about the specific state being evaluated, allowing the formulation of the equations to facilitate better solver selection and faster LP solving. The usefulness of the method is demonstrated in six domains and is shown to enhance performance significantly.