Charalampos P. Andriotis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Charalampos P. Andriotis has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Pablo Gabriel Morato
Engineering Risk Analysis Group, Technical University of Munich, Munich, Germany
2 shared publications - Prateek Bhustali
TU Delft
2 shared publications - Alessandra Luna-Navarro
Delft University of Technology
1 shared publication - Diederik M. Roijers
City of Amsterdam, Amsterdam, The Netherlands
1 shared publication - Jesse van Remmerden
Dept. of Industrial Engineering and Innovation Sciences Information Systems Eindhoven University of Technology (TU/e
1 shared publication K.G. Papakonstantinou
1 shared publication
Latest Publications
- Open Access
- 10 January 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (30) , 24719-24742
Deep multi-objective reinforcement learning for utility-based infrastructural maintenance optimization
In this paper, we introduce multi-objective deep centralized multi-agent actor-critic (MO-DCMAC), a multi-objective reinforcement learning method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is nonlinear. We evaluated MO-DCMAC using two utility functions, which use probability of collapse and cost as input. The first utility function is the threshold utility, in which MO-DCMAC should minimize cost so that the probability of collapse is never above the threshold. The second is based on the failure mode, effects, and criticality analysis methodology used by asset managers to assess maintenance plans. We evaluated MO-DCMAC, with both utility functions, in multiple maintenance environments, including ones based on a case study of the historical quay walls of Amsterdam. The performance of MO-DCMAC was compared against multiple rule-based policies based on heuristics currently used for constructing maintenance plans. Our results demonstrate that MO-DCMAC outperforms traditional rule-based policies across various environments and utility functions.
- 10 January 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (30) , 24719-24742
Open AccessDeep multi-objective reinforcement learning for utility-based infrastructural maintenance optimization
In this paper, we introduce multi-objective deep centralized multi-agent actor-critic (MO-DCMAC), a multi-objective reinforcement learning method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is nonlinear. We evaluated MO-DCMAC using two utility functions, which use probability of collapse and cost as input. The first utility function is the threshold utility, in which MO-DCMAC should minimize cost so that the probability of collapse is never above the threshold. The second is based on the failure mode, effects, and criticality analysis methodology used by asset managers to assess maintenance plans. We evaluated MO-DCMAC, with both utility functions, in multiple maintenance environments, including ones based on a case study of the historical quay walls of Amsterdam. The performance of MO-DCMAC was compared against multiple rule-based policies based on heuristics currently used for constructing maintenance plans. Our results demonstrate that MO-DCMAC outperforms traditional rule-based policies across various environments and utility functions.
- 23 December 2024
- Published by Springer Nature
- p. 203-210
Personalised Building Controls Based on Individual Thermal Preferences for Energy Efficiency and Thermal Comfort
- 23 December 2024
- Published by Springer Nature
- p. 203-210
Personalised Building Controls Based on Individual Thermal Preferences for Energy Efficiency and Thermal Comfort
- 2 November 2024
- Published by Springer Nature
- p. 236-254
Assessing the Optimality of Decentralized Inspection and Maintenance Policies for Stochastically Degrading Engineering Systems
- 2 November 2024
- Published by Springer Nature
- p. 236-254
Assessing the Optimality of Decentralized Inspection and Maintenance Policies for Stochastically Degrading Engineering Systems
- Top Cited Papers
- 11 February 2023
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 235
Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning
- 11 February 2023
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 235
Top Cited PapersInference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning