Goal-directed graph construction using reinforcement learning

نویسندگان

چکیده

Graphs can be used to represent and reason about systems a variety of metrics have been devised quantify their global characteristics. However, little is currently known how construct graph or improve an existing one given target objective. In this work, we formulate the construction as decision-making process in which central agent creates topologies by trial error receives rewards proportional value By means conceptual framework, propose algorithm based on reinforcement learning neural networks learn improvement strategies. Our core case study focuses robustness failures attacks, property relevant for infrastructure communication that power modern society. Experiments synthetic real-world graphs show approach outperform methods while being cheaper evaluate. It also allows generalization out-of-sample graphs, well larger out-of-distribution some cases. The applicable optimization other structural properties graphs.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning Goal-Directed Behaviour

Learning behaviour of artificial agents is commonly studied in the framework of Reinforcement Learning. Reinforcement Learning gained increasing popularity in the past years. This is partially due to developments that enabled the possibility to employ complex function approximators, such as deep networks, in combination with the framework. Two of the core challenges in Reinforcement Learning ar...

متن کامل

Construction in a Simulated Environment Using Temporal Goal Sequencing and Reinforcement Learning

A behavior-based architecture (ConAg) with a connectionist action selection mechanism is introduced that enables a society of autonomous agents to construct arbitrary structures in their simulated two-dimensional world. Construction in this environment involves the agents picking up colored discs and dropping them at incomplete parts of the structure being built. The ConAg architecture provides...

متن کامل

Information Directed reinforcement learning

Efficient exploration is recognized as a key difficulty in reinforcement learning. We consider an episodic undiscounted MDP where the goal is to minimize the sum of regrets over different episodes. Classical methods are either based on optimism in the face of uncertainty or on probability matching. In this project we explore an approach that aims at quantifying the cost of exploration while rem...

متن کامل

Goal-directed Learning to Fly

Learning to fly an aircraft is a complex task that requires the development of control skills and goal achievement strategies. This paper presents a behavioural cloning system that learns to successfully fly manoeuvres, in turbulence, of a realistic aircraft simulation. A hierarchical decomposition of the problem is employed where goal settings and the control skill to achieve them are learnt. ...

متن کامل

Efficient Construction of Dictionary using Directed Acyclic Word Graph

Implementation of dictionary is a topic on which research is going on since a long time in the search of a better and efficient algorithm both in terms of space and time complexity. Its necessity has increased due to the advent of recent technical advances in the fields of Pattern Recognition, Image Processing, Natural Language Processing and Machine Learning. The matter is of utter importance ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of The Royal Society A: Mathematical, Physical and Engineering Sciences

سال: 2021

ISSN: ['1471-2946', '1364-5021']

DOI: https://doi.org/10.1098/rspa.2021.0168