Probabilistic Constraint

Probabilistic constraint methods address the challenge of incorporating uncertainty and safety requirements into optimization and decision-making problems, particularly within machine learning and control systems. Current research focuses on developing efficient algorithms, such as those based on convex optimization and Bayesian inference, to integrate probabilistic constraints into various model architectures, including probabilistic circuits, reinforcement learning frameworks, and control barrier functions. These advancements are crucial for improving the reliability and safety of autonomous systems, particularly in safety-critical applications like robotics and healthcare, by enabling the design of robust and reliable systems that account for inherent uncertainties. The resulting methods offer a more nuanced approach to optimization, balancing optimality with the satisfaction of probabilistic constraints.

Papers

November 11, 2024

Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning
Andrey Zhitnikov, Vadim Indelman
Robot Person Monte Carlo Tree Search Risk Prediction Goal Directed Continuous Domain Probabilistic Constraint Anytime Valid Sequential Inference

June 18, 2024

Unlocking the Potential of Early Epochs: Uncertainty-aware CT Metal Artifact Reduction
Xinquan Yang, Guanqun Zhou, Wei Sun, Youjian Zhang, Zhongya Wang, Jiahui He, Zhicheng Zhang
Full Potential Metal Artifact Reduction Precise Inter EPOCH Feature Probabilistic Constraint

March 19, 2024

Probabilistic Circuits with Constraints via Convex Optimization
Soroush Ghandi, Benjamin Quost, Cassio de Campos
Convex Optimization Participation Constraint Probabilistic Circuit Deep Probabilistic Model Probabilistic Constraint Marginal Probability

March 4, 2024

Bayesian Constraint Inference from User Demonstrations Based on Margin-Respecting Preference Models
Dimitris Papadimitriou, Daniel S. Brown
Participation Constraint Video Demonstration Preference Model Probabilistic Constraint Constraint Inference

October 5, 2023

Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards
Zhaorun Chen, Zhuokai Zhao, Tairan He, Binhao Chen, Xuhao Zhao, Liang Gong, Chengliang Liu
Reinforcement Learning Safe Reinforcement Learning Safety Guarantee Probabilistic Constraint

July 3, 2023

Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning
Shengbo Wang, Ke Li, Yin Yang, Yuting Cao, Tingwen Huang, Shiping Wen
Meta Learning Probabilistic Safety Probabilistic Constraint

June 29, 2023

Probabilistic Constraint for Safety-Critical Reinforcement Learning
Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain
Reinforcement Learning Constrained Reinforcement Learning Primal Dual Algorithm Probabilistic Constraint

February 13, 2023

Simplified Continuous High Dimensional Belief Space Planning with Adaptive Probabilistic Belief-dependent Constraints
Andrey Zhitnikov, Vadim Indelman
Belief Space Planning Continuous POMDP Probabilistic Constraint

December 19, 2022

Fully Probabilistic Design for Optimal Transport
Sarah Boufelja Y., Anthony Quinn, Martin Corless, Robert Shorten
Optimal Transport Experimental Design Optimal Design Probabilistic Constraint

October 2, 2022

Policy Gradients for Probabilistic Constrained Reinforcement Learning
Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain
Reinforcement Learning Policy Gradient Policy Optimization Constrained Reinforcement Learning Probabilistic Safety Probabilistic Constraint Policy Based Algorithm

January 20, 2022

Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning
Jaeyoung Lee, Sean Sedwards, Krzysztof Czarnecki
Markov Decision Process Constrained Reinforcement Learning Deterministic Policy Logical Constraint Stable Learning Probabilistic Constraint Constrained Reinforcement Learning Algorithm

Probabilistic Constraint

Papers

Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning

Unlocking the Potential of Early Epochs: Uncertainty-aware CT Metal Artifact Reduction

Probabilistic Circuits with Constraints via Convex Optimization

Bayesian Constraint Inference from User Demonstrations Based on Margin-Respecting Preference Models

Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards

Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning

Probabilistic Constraint for Safety-Critical Reinforcement Learning

Simplified Continuous High Dimensional Belief Space Planning with Adaptive Probabilistic Belief-dependent Constraints

Fully Probabilistic Design for Optimal Transport

Policy Gradients for Probabilistic Constrained Reinforcement Learning

Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning