Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Kaixin, Gadot, Uri, Kumar, Navdeep, Levy, Kfir, Mannor, Shie
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929239757946880
author Wang, Kaixin
Gadot, Uri
Kumar, Navdeep
Levy, Kfir
Mannor, Shie
author_facet Wang, Kaixin
Gadot, Uri
Kumar, Navdeep
Levy, Kfir
Mannor, Shie
contents Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, current RMDP methods are often limited to small-scale problems, hindering their use in high-dimensional domains. To bridge this gap, we present EWoK, a novel online approach to solve RMDP that Estimates the Worst transition Kernel to learn robust policies. Unlike previous works that regularize the policy or value updates, EWoK achieves robustness by simulating the worst scenarios for the agent while retaining complete flexibility in the learning process. Notably, EWoK can be applied on top of any off-the-shelf {\em non-robust} RL algorithm, enabling easy scaling to high-dimensional domains. Our experiments, spanning from simple Cartpole to high-dimensional DeepMind Control Suite environments, demonstrate the effectiveness and applicability of the EWoK paradigm as a practical method for learning robust policies.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05859
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
Wang, Kaixin
Gadot, Uri
Kumar, Navdeep
Levy, Kfir
Mannor, Shie
Machine Learning
Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, current RMDP methods are often limited to small-scale problems, hindering their use in high-dimensional domains. To bridge this gap, we present EWoK, a novel online approach to solve RMDP that Estimates the Worst transition Kernel to learn robust policies. Unlike previous works that regularize the policy or value updates, EWoK achieves robustness by simulating the worst scenarios for the agent while retaining complete flexibility in the learning process. Notably, EWoK can be applied on top of any off-the-shelf {\em non-robust} RL algorithm, enabling easy scaling to high-dimensional domains. Our experiments, spanning from simple Cartpole to high-dimensional DeepMind Control Suite environments, demonstrate the effectiveness and applicability of the EWoK paradigm as a practical method for learning robust policies.
title Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
topic Machine Learning
url https://arxiv.org/abs/2306.05859