[HTML][HTML] Deep reinforcement learning for process design: Review and perspective

Q Gao, AM Schweidtmann - Current Opinion in Chemical Engineering, 2024‏ - Elsevier
The transformation toward renewable energy and feedstock supply in the chemical industry
requires new conceptual process design approaches. Recently, deep reinforcement …

Decision-making under uncertainty: beyond probabilities: Challenges and perspectives

T Badings, TD Simão, M Suilen, N Jansen - International Journal on …, 2023‏ - Springer
This position paper reflects on the state-of-the-art in decision-making under uncertainty. A
classical assumption is that probabilities can sufficiently capture all uncertainty in a system …

Foundations of multivariate distributional reinforcement learning

H Wiltzer, J Farebrother, A Gretton… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
In reinforcement learning (RL), the consideration of multivariate reward signals has led to
fundamental advancements in multi-objective decision-making, transfer learning, and …

Uncertainty-aware constraint inference in inverse constrained reinforcement learning

S Xu, G Liu - The Twelfth International Conference on Learning …, 2023‏ - openreview.net
Aiming for safe control, Inverse Constrained Reinforcement Learning (ICRL) considers
inferring the constraints respected by expert agents from their demonstrations and learning …

Cem: Constrained entropy maximization for task-agnostic safe exploration

Q Yang, MTJ Spaan - Proceedings of the AAAI Conference on Artificial …, 2023‏ - ojs.aaai.org
In the absence of assigned tasks, a learning agent typically seeks to explore its environment
efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored …

Trust region-based safe distributional reinforcement learning for multiple constraints

D Kim, K Lee, S Oh - Advances in neural information …, 2023‏ - proceedings.neurips.cc
In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints
must be met, such as avoiding collisions, limiting energy consumption, and maintaining …

[HTML][HTML] Constrained continuous-action reinforcement learning for supply chain inventory management

R Burtea, C Tsay - Computers & Chemical Engineering, 2024‏ - Elsevier
Reinforcement learning (RL) is a promising solution for difficult decision-making problems,
such as inventory management in chemical supply chains. However, enabling RL to …

Feasible reachable policy iteration

S Qin, Y Yang, Y Mu, J Li, W Zou, J Duan… - Forty-first International …, 2024‏ - openreview.net
The goal-reaching tasks with safety constraints are common control problems in real world,
such as intelligent driving and robot manipulation. The difficulty of this kind of problem …

Safe reinforcement learning on the constraint manifold: Theory and applications

P Liu, H Bou-Ammar, J Peters, D Tateo - arxiv preprint arxiv:2404.09080, 2024‏ - arxiv.org
Integrating learning-based techniques, especially reinforcement learning, into robotics is
promising for solving complex problems in unstructured environments. However, most …

Resilient constrained learning

I Hounie, A Ribeiro… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
When deploying machine learning solutions, they must satisfy multiple requirements beyond
accuracy, such as fairness, robustness, or safety. These requirements are imposed during …