Efficient Black-Box Planning Using Macro-Actions with Focused Effects
This addresses the challenge of deterministic planning in black-box settings for AI and robotics, offering a novel method to enhance heuristic-based search.
The paper tackled the problem of inefficient black-box planning due to uninformative goal-count heuristics by discovering macro-actions with focused effects to improve heuristic accuracy, resulting in dramatic efficiency gains across planning domains, sometimes outperforming state-of-the-art planners with full domain models.
The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heuristics can make search more efficient, but goal-aware heuristics for black-box planning usually rely on goal counting, which is often quite uninformative. In this work, we show how to overcome this limitation by discovering macro-actions that make the goal-count heuristic more accurate. Our approach searches for macro-actions with focused effects (i.e. macros that modify only a small number of state variables), which align well with the assumptions made by the goal-count heuristic. Focused macros dramatically improve black-box planning efficiency across a wide range of planning domains, sometimes beating even state-of-the-art planners with access to a full domain model.