paper-with-me

홈 › Papers

Learning Rational Subgoals from Demonstrations and Instructions

2023-03-09 · Zhezheng Luo, Jiayuan Mao, Jiajun Wu, Tomás Lozano-Pérez, Joshua B. Tenenbaum, Leslie Pack Kaelbling

We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-annotated data, in the form of unsegmented demonstration trajectories, paired with abstract task descriptions, which are composed of terms initially unknown to the agent (e.g., collect-wood then craft-boat then go-across-river). Our framework also discovers dependencies between RSGs, e.g., the task collect-wood is a helpful subgoal for the task craft-boat. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT, by setting helpful subgoals as waypoints to the planner, which significantly improves performance-time efficiency.

📄 PDF Abstract BibTeX arXiv:2303.05487

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Toward a normative theory of (self-)management by goal-setting

2023-02-06 · Nishad Singhi, Florian Mohnert, Ben Prystawski, Falk Lieder

People are often confronted with problems whose complexity exceeds their cognitive capacities. To deal with this complexity, individuals and managers can break complex problems down into a series of subgoals. Which subgo…

Management

Modular Networks for Compositional Instruction Following

2020-10-24 · NAACL 2021 4 · Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein 외

Standard architectures used in instruction following often struggle on novel compositions of subgoals (e.g. navigating to landmarks or picking up objects) observed during training. We propose a modular architecture for f…

Instruction Following

Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning

2025-08-12 · Ben Zandonati, Tomás Lozano-Pérez, Leslie Pack Kaelbling arxiv

Humans can learn a new manipulation task from one or two demonstrations and then perform it in a new room, with new objects, under new constraints. Modern robot imitation learning, in contrast, typically needs hundreds t…

PRISM: Recovering Instruction Sets from Language Model Activations

2026-06-08 · Gilad Gressel, Rahul Pankajakshan, Julia Diament, Efim Hudis 외 arxiv

As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior. This is difficult when models infer unintended subgoals, follow contextu…

Enhancing Cognitive Robotics with Commonsense through LLM-Generated Preconditions and Subgoals

2025-11-24 · Ohad Bachner, Bar Gamliel arxiv

Robots often fail at everyday tasks because instructions skip commonsense details like hidden preconditions and small subgoals. Traditional symbolic planners need these details to be written explicitly, which is time con…