Reinforcement learning for autonomous process control in industry 4.0: Advantages and challenges

N Nievas, A Pagès-Bernaus, F Bonada… - Applied Artificial …, 2024 - Taylor & Francis
In recent years, the integration of intelligent industrial process monitoring, quality prediction,
and predictive maintenance solutions has garnered significant attention, driven by rapid …

A Survey of Constraint Formulations in Safe Reinforcement Learning

A Wachi, X Shen, Y Sui - ar**-based Policy for Chance-Constrained Markov Decision Processes
X Shen, S Jiang, A Wachi, K Hashimoto… - arxiv preprint arxiv …, 2024 - arxiv.org
Safe reinforcement learning (RL) is a promising approach for many real-world decision-
making problems where ensuring safety is a critical necessity. In safe RL research, while …

Preparing for Black Swans: The Antifragility Imperative for Machine Learning

M ** - arxiv preprint arxiv:2405.11397, 2024 - arxiv.org
Operating safely and reliably despite continual distribution shifts is vital for high-stakes
machine learning applications. This paper builds upon the transformative concept …

SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP

S Mukherjee, JP Hanna, R Nowak - arxiv preprint arxiv:2406.02165, 2024 - arxiv.org
In this paper, we study safe data collection for the purpose of policy evaluation in tabular
Markov decision processes (MDPs). In policy evaluation, we are given a\textit {target} policy …

Safe Policy Optimization With Stretchable Penalties

N Pang, L Huang, B Dong, H Chen, Z Jia… - Authorea Preprints, 2024 - techrxiv.org
In safe reinforcement learning (RL), ensuring cost-constraint satisfaction while minimizing
the sacrifice of reward acquisition for agent training presents a significant challenge. This …

[PDF][PDF] Safe Resetless Reinforcement Learning: Enhancing Training Autonomy with Risk-Averse Agents

T Gottwald, M Schier, B Rosenhahn - tnt.uni-hannover.de
Training Reinforcement Learning agents directly in any realworld environment remains
difficult, as such scenarios entail the risk of damaging the training setup or violating other …