Safe Exploration Using Bayesian World Models and Log-Barrier Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: As, Yarden, Sukhija, Bhavya, Krause, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914789466308608
author As, Yarden
Sukhija, Bhavya
Krause, Andreas
author_facet As, Yarden
Sukhija, Bhavya
Krause, Andreas
contents A major challenge in deploying reinforcement learning in online tasks is ensuring that safety is maintained throughout the learning process. In this work, we propose CERL, a new method for solving constrained Markov decision processes while keeping the policy safe during learning. Our method leverages Bayesian world models and suggests policies that are pessimistic w.r.t. the model's epistemic uncertainty. This makes CERL robust towards model inaccuracies and leads to safe exploration during learning. In our experiments, we demonstrate that CERL outperforms the current state-of-the-art in terms of safety and optimality in solving CMDPs from image observations.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05890
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Safe Exploration Using Bayesian World Models and Log-Barrier Optimization
As, Yarden
Sukhija, Bhavya
Krause, Andreas
Machine Learning
Artificial Intelligence
A major challenge in deploying reinforcement learning in online tasks is ensuring that safety is maintained throughout the learning process. In this work, we propose CERL, a new method for solving constrained Markov decision processes while keeping the policy safe during learning. Our method leverages Bayesian world models and suggests policies that are pessimistic w.r.t. the model's epistemic uncertainty. This makes CERL robust towards model inaccuracies and leads to safe exploration during learning. In our experiments, we demonstrate that CERL outperforms the current state-of-the-art in terms of safety and optimality in solving CMDPs from image observations.
title Safe Exploration Using Bayesian World Models and Log-Barrier Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.05890