paper-with-me

홈 › Papers

Automata Guided Skill Composition

2019-05-01 · ICLR 2019 5 · Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task. We present a framework that combines techniques in formal methods with reinforcement learning (RL) that allows for the convenient specification of complex temporal dependent tasks with logical expressions and construction of new skills from existing ones with no additional exploration. We provide theoretical results for our composition technique and evaluate on a simple grid world simulation as well as a robotic manipulation task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Automata-Guided Hierarchical Reinforcement Learning for Skill Composition

2017-10-31 · Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework that combines techniques in \textit{formal …

Deep Reinforcement LearningHierarchical Reinforcement Learningreinforcement-learningReinforcement Learning+1

AUTOMATA GUIDED HIERARCHICAL REINFORCEMENT LEARNING FOR ZERO-SHOT SKILL COMPOSITION

2018-01-01 · ICLR 2018 1 · Xiao Li, Yao Ma, Calin Belta

An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill. The learned skill usual…

Deep Reinforcement LearningHierarchical Reinforcement Learningreinforcement-learningReinforcement Learning+1

CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action

2026-08-28 · Lekai Chen, Alvaro Velasquez, Ashutosh Trivedi arxiv

Natural-language tasking of embodied agents is rarely just goal specification: users also impose constraints that must persist while the world changes. Code-generating LLM agents can produce plausible behaviors for such …

Automata Cascades: Expressivity and Sample Complexity

2022-11-25 · Alessandro Ronca, Nadezda Alexandrovna Knorozova, Giuseppe De Giacomo

Every automaton can be decomposed into a cascade of basic prime automata. This is the Prime Decomposition Theorem by Krohn and Rhodes. Guided by this theory, we propose automata cascades as a structured, modular, way to …

Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis

2026-01-07 · Yifan Wei, Li Du, Xiaoyan Yu, Yang Feng 외 arxiv

Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting bo…