Goal-Driven Sequential Data Abstraction

2019-07-29 · ICCV 2019 10 · Umar Riaz Muhammad, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely allows different aspects of the input data to be preserved according to the ultimate purpose of the abstraction. Our reinforcement learning objective does not require human-defined examples of ideal abstraction. Importantly our model processes the input sequence holistically without being constrained by the original input order. Our framework is also domain agnostic -- we demonstrate applications to sketch, video and text data and achieve promising results in all domains.

📄 PDF Abstract BibTeX arXiv:1907.12336

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking General Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks

2026-08-04 · Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich Gaba arxiv

Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon sequential decision…

Reinforcement Learning

Data-driven memory-dependent abstractions of dynamical systems

2022-12-04 · Adrien Banse, Licio Romao, Alessandro Abate, Raphaël M. Jungers

We propose a sample-based, sequential method to abstract a (potentially black-box) dynamical system with a sequence of memory-dependent Markov chains of increasing size. We show that this approximation allows to alleviat…

Learning Discrete State Abstractions With Deep Variational Inference

2020-03-09 · pproximateinference AABI Symposium 2021 1 · Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong

Abstraction is crucial for effective sequential decision making in domains with large state spaces. In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstra…

Decision Making Multi-Goal Reinforcement Learning Reinforcement Learning Sequential Decision Making+1

Planning with Goal-Conditioned Policies

2019-11-19 · NeurIPS 2019 12 · Soroush Nasiriany, Vitchyr H. Pong, Steven Lin, Sergey Levine

Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to b…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+3

Sequential Diagnosis by Abstraction

2014-01-16 · Sajjad Ahmed Siddiqi, Jinbo Huang

When a system behaves abnormally, sequential diagnosis takes a sequence of measurements of the system until the faults causing the abnormality are identified, and the goal is to reduce the diagnostic cost, defined here a…

Diagnostic Sequential Diagnosis