Picture for Mouhacine Benosman

Mouhacine Benosman

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Jan 30, 2023
James Queeney, Mouhacine Benosman

Figure 1 for Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Figure 2 for Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Figure 3 for Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Figure 4 for Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Access Paper or Ask Questions

Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

Apr 27, 2022
Weidong Cao, Mouhacine Benosman, Xuan Zhang, Rui Ma

Figure 1 for Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

Figure 2 for Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

Figure 3 for Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

Figure 4 for Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

* 7 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:2202.13185

Access Paper or Ask Questions

Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

Feb 26, 2022
Weidong Cao, Mouhacine Benosman, Xuan Zhang, Rui Ma

Figure 1 for Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

Figure 2 for Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

Figure 3 for Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

Figure 4 for Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

* 8 pages, 5 figures, 2 tables, Thirty-Sixth AAAI Conference on Artificial Intelligence, The 1st Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE)

Access Paper or Ask Questions

Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty

Aug 05, 2021
Reazul Hasan Russel, Mouhacine Benosman, Jeroen Van Baar, Radu Corcodel

Access Paper or Ask Questions

Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

Oct 10, 2020
Reazul Hasan Russel, Mouhacine Benosman, Jeroen Van Baar

Figure 1 for Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

Access Paper or Ask Questions

Safe Learning-based Observers for Unknown Nonlinear Systems using Bayesian Optimization

May 12, 2020
Ankush Chakrabarty, Mouhacine Benosman

Figure 1 for Safe Learning-based Observers for Unknown Nonlinear Systems using Bayesian Optimization

Figure 2 for Safe Learning-based Observers for Unknown Nonlinear Systems using Bayesian Optimization

* 20 pages, pre-submission draft

Access Paper or Ask Questions

Finite-Time Convergence of Continuous-Time Optimization Algorithms via Differential Inclusions

Dec 18, 2019
Orlando Romero, Mouhacine Benosman

Figure 1 for Finite-Time Convergence of Continuous-Time Optimization Algorithms via Differential Inclusions

* Presented at workshop "Beyond First Order Methods in Machine Learning" of NeurIPS 2019

Access Paper or Ask Questions