Optimal Stopping via Randomized Neural Networks

04/28/2021
by   Calypso Herrera, et al.
0

This paper presents new machine learning approaches to approximate the solution of optimal stopping problems. The key idea of these methods is to use neural networks, where the hidden layers are generated randomly and only the last layer is trained, in order to approximate the continuation value. Our approaches are applicable for high dimensional problems where the existing approaches become increasingly impractical. In addition, since our approaches can be optimized using a simple linear regression, they are very easy to implement and theoretical guarantees can be provided. In Markovian examples our randomized reinforcement learning approach and in non-Markovian examples our randomized recurrent neural network approach outperform the state-of-the-art and other relevant machine learning approaches.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

09/11/2020

QRnet: optimal regulator design with LQR-augmented neural networks

In this paper we propose a new computational method for designing optima...
02/08/2021

Introduction to Machine Learning for the Sciences

This is an introductory machine learning course specifically developed w...
02/03/2020

Randomized optimal stopping algorithms and their convergence analysis

In this paper we study randomized optimal stopping problems and consider...
06/08/2020

Randomized Policy Learning for Continuous State and Action MDPs

Deep reinforcement learning methods have achieved state-of-the-art resul...
08/07/2018

Optimal stopping via deeply boosted backward regression

In this note we propose a new approach towards solving numerically optim...
12/18/2018

Interpretable Optimal Stopping

Optimal stopping is the problem of deciding when to stop a stochastic sy...
06/19/2017

Unsure When to Stop? Ask Your Semantic Neighbors

In iterative supervised learning algorithms it is common to reach a poin...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.