Object-oriented state editing for HRL

10/31/2019
by   Victor Bapst, et al.
0

We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical controller directs a low-level agent to behave as if objects in the scene were added, deleted, or modified. The actions taken by the controller are defined over a graph-based representation of the scene, with actions corresponding to adding, deleting, or editing the nodes of a graph. We present preliminary results on three environments, demonstrating that our approach can achieve similar levels of reward as non-hierarchical agents, but with better data efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/20/2017

Learning to Act Properly: Predicting and Explaining Affordances from Images

We address the problem of affordance reasoning in diverse scenes that ap...
research
06/11/2020

From proprioception to long-horizon planning in novel environments: A hierarchical RL model

For an intelligent agent to flexibly and efficiently operate in complex ...
research
10/17/2019

Faster parameterized algorithm for Bicluter Editing

In the Bicluter Editing problem the input is a graph G and an integer k,...
research
03/26/2023

BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes

3D-aware image synthesis has attracted increasing interest as it models ...
research
07/01/2019

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning

In many real-world scenarios, an autonomous agent often encounters vario...
research
02/25/2022

Hierarchical Control for Multi-Agent Autonomous Racing

We develop a hierarchical controller for multi-agent autonomous racing. ...
research
05/17/2021

SHARE: a System for Hierarchical Assistive Recipe Editing

We introduce SHARE: a System for Hierarchical Assistive Recipe Editing t...

Please sign up or login with your details

Forgot password? Click here to reset