Deep reinforcement learning (DRL) has proven capable of superhuman performance on many complex tasks. To achieve this success, DRL algorithms train a decision-making agent …
J Tian, D Zhi, S Liu, P Wang… - Advances in Neural …, 2023 - proceedings.neurips.cc
Formally verifying deep reinforcement learning (DRL) systems suffers from both inaccurate verification results and limited scalability. The major obstacle lies in the large overestimation …
U Mandal, G Amir, H Wu, I Daukantas… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the" black box" nature of DRL agents …
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 …
Model-based reinforcement learning has been widely studied for controller synthesis in cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …
E Bacci, D Parker - Formal Modeling and Analysis of Timed Systems: 18th …, 2020 - Springer
Deep reinforcement learning has been successfully applied to many control tasks, but the application of such controllers in safety-critical scenarios has been limited due to safety …
G Amir, M Schapira, G Katz - 2021 formal methods in computer …, 2021 - library.oapen.org
Deep neural networks (DNNs) have gained significant popularity in recent years, becoming the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) …
E Bacci, D Parker - NASA Formal Methods Symposium, 2022 - Springer
Deep reinforcement learning is an increasingly popular technique for synthesising policies to control an agent's interaction with its environment. There is also growing interest in …
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of decision-making problems, from resource management to robot …