paper-with-me

Papers

Generating Plannable Lifted Action Models for Visually Generated Logical Predicates

2021-01-01 · Masataro Asai

We propose FOSAE++, an unsupervised end-to-end neural system that generates a compact discrete state transition model (dynamics / action model) from raw visual observations. Our representation can be exported to Planning Domain Description Language (PDDL), allowing symbolic state-of-the-art classical planners to perform high-level task planning on raw observations. FOSAE++ expresses states and actions in First Order Logic (FOL), a superset of so-called object-centric representation. It is the first unsupervised neural system that fully supports FOL in PDDL action modeling, while existing systems are limited to continuous, propositional, or property-based representations, and/or require manually labeled input.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Task Planning

Similar Papers 제목 키워드 기반

Plannable Approximations to MDP Homomorphisms: Equivariance under Actions

2020-02-27 · Elise van der Pol, Thomas Kipf, Frans A. Oliehoek, Max Welling

This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, …

Reinforcement LearningRepresentation Learning

Procedure Planning in Instructional Videos

2019-07-02 · ECCV 2020 8 · Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli 외

In this paper, we study the problem of procedure planning in instructional videos, which can be seen as a step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking. Given the …

Lifting Embodied World Models for Planning and Control

2026-04-28 · Alex N. Wang, Trevor Darrell, Pavel Izmailov, Yutong Bai 외 arxiv

World models of embodied agents predict future observations conditioned on an action taken by the agent. For complex embodiments, action spaces are high-dimensional and difficult to specify: for example, precisely contro…

Generating and Sampling Orbits for Lifted Probabilistic Inference

2019-03-12 · Steven Holtzen, Todd Millstein, Guy Van Den Broeck

A key goal in the design of probabilistic inference algorithms is identifying and exploiting properties of the distribution that make inference tractable. Lifted inference algorithms identify symmetry as a property that …

Inference in Probabilistic Logic Programs using Lifted Explanations

2016-08-20 · Arun Nampally, C. R. Ramakrishnan

In this paper, we consider the problem of lifted inference in the context of Prism-like probabilistic logic programming languages. Traditional inference in such languages involves the construction of an explanation graph…