Online safety assurance for deep reinforcement learning
Recently, deep learning has been successfully applied to a variety of networking problems.
A fundamental challenge is that when the operational environment for a learning …
A fundamental challenge is that when the operational environment for a learning …
Online safety assurance for learning-augmented systems
Recently, deep learning has been successfully applied to a variety of networking problems.
A fundamental challenge is that when the operational environment for a learning …
A fundamental challenge is that when the operational environment for a learning …
Verification-Guided Shielding for Deep Reinforcement Learning
In recent years, Deep Reinforcement Learning (DRL) has emerged as an effective approach
to solving real-world tasks. However, despite their successes, DRL-based policies suffer …
to solving real-world tasks. However, despite their successes, DRL-based policies suffer …
Safe deep reinforcement learning by verifying task-level properties
Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL).
However, the cost is typically encoded as an indicator function due to the difficulty of …
However, the cost is typically encoded as an indicator function due to the difficulty of …
BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions
X Liu, J Zhao, W Chen, M Tan, Y Su - arXiv preprint arXiv:2401.07263, 2024 - arxiv.org
Despite the impressive capabilities of Deep Reinforcement Learning (DRL) agents in many
challenging scenarios, their black-box decision-making process significantly limits their …
challenging scenarios, their black-box decision-making process significantly limits their …
Risk sensitive dead-end identification in safety-critical offline reinforcement learning
In safety-critical decision-making scenarios being able to identify worst-case outcomes, or
dead-ends is crucial in order to develop safe and reliable policies in practice. These …
dead-ends is crucial in order to develop safe and reliable policies in practice. These …
Safe reinforcement learning using advantage-based intervention
NC Wagener, B Boots… - … Conference on Machine …, 2021 - proceedings.mlr.press
Many sequential decision problems involve finding a policy that maximizes total reward
while obeying safety constraints. Although much recent research has focused on the …
while obeying safety constraints. Although much recent research has focused on the …
DSMC Evaluation Stages: Fostering Robust and Safe Behavior in Deep Reinforcement Learning–Extended Version
Neural networks (NN) are gaining importance in sequential decision-making. Deep
reinforcement learning (DRL), in particular, is extremely successful in learning action …
reinforcement learning (DRL), in particular, is extremely successful in learning action …
Dsmc evaluation stages: Fostering robust and safe behavior in deep reinforcement learning
Neural networks (NN) are gaining importance in sequential decision-making. Deep
reinforcement learning (DRL), in particular, is extremely successful in learning action …
reinforcement learning (DRL), in particular, is extremely successful in learning action …
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
Among approaches for provably safe reinforcement learning, Model Predictive Shielding
(MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces …
(MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces …