# Efficient Black-Box Planning Using Macro-Actions with Focused Effects

arXiv: https://arxiv.org/abs/2004.13242 · HTML: https://mlsanity.com/paper/2004.13242/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search](https://mlsanity.com/paper/2206.00702/) (2022)
- [Levin Tree Search with Context Models](https://mlsanity.com/paper/2305.16945/) (2023)
- [Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference](https://mlsanity.com/paper/2412.14355/) (2024)
- [Hybrid Search for Efficient Planning with Completeness Guarantees](https://mlsanity.com/paper/2310.12819/) (2023)
- [Planning with Dynamically Estimated Action Costs](https://mlsanity.com/paper/2206.04166/) (2022)
- [Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik's Cube](https://mlsanity.com/paper/2402.01760/) (2024)
- [Meta-learning how to Share Credit among Macro-Actions](https://mlsanity.com/paper/2506.13690/) (2025)
- [Focused Skill Discovery: Learning to Control Specific State Variables while Minimizing Side Effects](https://mlsanity.com/paper/2510.04901/) (2025)

## Abstract (arXiv)

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.