English
Related papers

Related papers: Learning Planning Abstractions from Language

200 papers

We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide…

Machine Learning · Computer Science 2024-03-13 Huaixiu Steven Zheng , Swaroop Mishra , Xinyun Chen , Heng-Tze Cheng , Ed H. Chi , Quoc V Le , Denny Zhou

Learning diagnosis is a critical task that monitors students' cognitive state during educational activities, with the goal of enhancing learning outcomes. With advancements in language models (LMs), many AI-driven educational studies have…

Computers and Society · Computer Science 2026-03-04 Fangzhou Yao , Sheng Chang , Weibo Gao , Qi Liu

At its core, abstraction is the process of generalizing from specific instances to broader concepts or models, with the primary objective of reducing complexity while preserving properties essential to the intended purpose. It is…

Logic in Computer Science · Computer Science 2026-01-06 Andrzej Szalas

Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process…

Computation and Language · Computer Science 2020-11-19 Nurul Lubis , Christian Geishauser , Michael Heck , Hsien-chin Lin , Marco Moresi , Carel van Niekerk , Milica Gašić

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Machine Learning · Computer Science 2023-10-03 Wenhao Li

Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during…

Robotics · Computer Science 2024-05-31 Muzhi Han , Yifeng Zhu , Song-Chun Zhu , Ying Nian Wu , Yuke Zhu

Large language models excel with reinforcement learning (RL), but fully unlocking this potential requires a mid-training stage. An effective mid-training phase should identify a compact set of useful actions and enable fast selection among…

Machine Learning · Computer Science 2025-10-14 Shenao Zhang , Donghan Yu , Yihao Feng , Bowen Jin , Zhaoran Wang , John Peebles , Zirui Wang

Large Language Models (LLMs) have shown remarkable reasoning ability through explicit Chain-of-Thought (CoT) prompting, but generating these step-by-step textual explanations is computationally expensive and slow. To overcome this, we aim…

Artificial Intelligence · Computer Science 2025-07-25 Chang Li , Yaren Zhang , Haoran Lv , Qiong Cao , Chao Xue , Xiaodong He

This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement learning architectures, specifically under the constraint of…

Machine Learning · Computer Science 2026-04-07 Daniel Bloch

Language agents have shown promising adaptability in dynamic environments to perform complex tasks. However, despite the versatile knowledge embedded in large language models, these agents still fall short when it comes to tasks that…

Computation and Language · Computer Science 2024-11-14 Minh Nguyen , Ehsan Shareghi

The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables sample-efficient learning. This becomes particularly beneficial in complex environments…

Artificial Intelligence · Computer Science 2023-10-17 Thomas Jiralerspong , Flemming Kondrup , Doina Precup , Khimya Khetarpal

In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the…

Computer Vision and Pattern Recognition · Computer Science 2016-09-29 Jia-xin Cai , Xin Tang , Lifang Zhang , Guocan Feng

We propose a framework for learning discrete deterministic planning domains. In this framework, an agent learns the domain by observing the action effects through continuous features that describe the state of the environment after the…

Artificial Intelligence · Computer Science 2019-04-22 Luciano Serafini , Paolo Traverso

Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially…

Machine Learning · Computer Science 2026-02-24 Baiting Luo , Yunuo Zhang , Nathaniel S. Keplinger , Samir Gupta , Abhishek Dubey , Ayan Mukhopadhyay

A common technique to verify complex logic specifications for dynamical systems is the construction of symbolic abstractions: simpler, finite-state models whose behaviour mimics the one of the systems of interest. Typically, abstractions…

Systems and Control · Electrical Eng. & Systems 2023-03-30 Rudi Coppola , Andrea Peruffo , Manuel Mazo

The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks. However, the performance of pre-trained models on the…

Computation and Language · Computer Science 2020-04-30 Jing Gu , Qingyang Wu , Chongruo Wu , Weiyan Shi , Zhou Yu

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state…

Machine Learning · Computer Science 2024-03-18 Cameron Allen , Neev Parikh , Omer Gottesman , George Konidaris

We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning. Given an image, we first predict a probabilistic…

Artificial Intelligence · Computer Science 2019-11-26 Drew A. Hudson , Christopher D. Manning

While end-to-end learning with fully differentiable models has enabled tremendous success in natural language process (NLP) and machine learning, there have been significant recent interests in learning with latent discrete structures to…

Computation and Language · Computer Science 2022-01-12 Zhaofeng Wu

Language acquisition is the process of learning words from the surrounding scene. We introduce a meta-learning framework that learns how to learn word representations from unconstrained scenes. We leverage the natural compositional…

Computation and Language · Computer Science 2020-07-14 Dídac Surís , Dave Epstein , Heng Ji , Shih-Fu Chang , Carl Vondrick