Exploring the hierarchical structure of human plans via program generation
Human behavior is often assumed to be hierarchically structured, made up of abstract actions that can be decomposed into concrete actions. However, behavior is typically measured as a sequence of actions, which makes it difficult to infer its hierarchical structure. In this paper, we explore how people form hierarchically structured plans, using an experimental paradigm with observable hierarchical representations: participants create programs that produce sequences of actions in a language with explicit hierarchical structure. This task lets us test two well-established principles of human behavior: utility maximization (i.e. using fewer actions) and minimum description length (MDL; i.e. having a shorter program). We find that humans are sensitive to both metrics, but that both accounts fail to predict a qualitative feature of human-created programs, namely that people prefer programs with reuse over and above the predictions of MDL. We formalize this preference for reuse by extending the MDL account into a generative model over programs, modeling hierarchy choice as the induction of a grammar over actions. Our account can explain the preference for reuse and provides better predictions of human behavior, going beyond simple accounts of compressibility to highlight a principle that guides hierarchical planning.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Hierarchy-Aware Inverse Reinforcement Learning
We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan using hierarchical strategies. We describ…
BIRLreinforcement-learningReinforcement LearningReinforcement Learning (RL)VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping
In argumentative writing, writers must brainstorm hierarchical writing goals, ensure the persuasiveness of their arguments, and revise and organize their plans through drafting. Recent advances in large language models (…
PersuasivenessText GenerationParsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithm…
Automated Theorem ProvingCode GenerationHumanEvalLanguage Modelling+3Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithm…
Reasoning about Study Regulations in Answer Set Programming
We are interested in automating reasoning with and about study regulations, catering to various stakeholders, ranging from administrators, over faculty, to students at different stages. Our work builds on an extensive an…