English
Related papers

Related papers: Scalable Safety-Critical Policy Evaluation with Ac…

200 papers

While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing. Real-world testing, the $\textit{de facto}$ evaluation environment, places the public in…

Machine Learning · Computer Science 2019-01-15 Matthew O'Kelly , Aman Sinha , Hongseok Namkoong , John Duchi , Russ Tedrake

An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo…

Machine Learning · Computer Science 2022-11-23 Anthony Corso , Kyu-Young Kim , Shubh Gupta , Grace Gao , Mykel J. Kochenderfer

Evaluating the reliability of intelligent physical systems against rare safety-critical events poses a huge testing burden for real-world applications. Simulation provides a useful platform to evaluate the extremal risks of these systems…

Machine Learning · Computer Science 2021-03-09 Mansur Arief , Zhiyuan Huang , Guru Koushik Senthil Kumar , Yuanlu Bai , Shengyi He , Wenhao Ding , Henry Lam , Ding Zhao

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Computation and Language · Computer Science 2025-06-10 Javier Marín

Reinforcement Learning aims at identifying and evaluating efficient control policies from data. In many real-world applications, the learner is not allowed to experiment and cannot gather data in an online manner (this is the case when…

Machine Learning · Computer Science 2024-07-02 Daniele Foffano , Alessio Russo , Alexandre Proutiere

Decision making in multi-agent systems (MAS) is a great challenge due to enormous state and joint action spaces as well as uncertainty, making centralized control generally infeasible. Decentralized control offers better scalability and…

Artificial Intelligence · Computer Science 2019-01-28 Thomy Phan , Kyrill Schmid , Lenz Belzner , Thomas Gabor , Sebastian Feld , Claudia Linnhoff-Popien

Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-world testing is prohibitively expensive and unscalable.…

Machine Learning · Computer Science 2021-08-10 Aman Sinha , Matthew O'Kelly , Russ Tedrake , John Duchi

Anomaly detection plays an important role in modern data-driven security applications, such as detecting suspicious access to a socket from a process. In many cases, such events can be described as a collection of categorical values that…

Machine Learning · Computer Science 2016-08-29 Ting Chen , Lu-An Tang , Yizhou Sun , Zhengzhang Chen , Kai Zhang

The efficient calculation of rare-event kinetics in complex dynamical systems, such as the rate and pathways of ligand dissociation from a protein, is a generally unsolved problem. Markov state models can systematically integrate ensembles…

Chemical Physics · Physics 2016-02-03 Benjamin Trendelkamp-Schroer , Frank Noe

Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of…

Robotics · Computer Science 2021-03-16 Visak Kumar , Sehoon Ha , C. Karen Liu

Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to…

Machine Learning · Computer Science 2022-09-20 Harvineet Singh , Shalmali Joshi , Finale Doshi-Velez , Himabindu Lakkaraju

Detecting rare events, those defined to give rise to high impact but have a low probability of occurring, is a challenge in a number of domains including meteorological, environmental, financial and economic. The use of machine learning to…

Applications · Statistics 2022-09-13 Santhosh Narayanan , Carsten Maple , Mark Hooper

The development of enhanced sampling methods has greatly extended the scope of atomistic simulations, allowing long-time phenomena to be studied with accessible computational resources. Many such methods rely on the identification of an…

Computational Physics · Physics 2022-06-08 Luigi Bonati , GiovanniMaria Piccini , Michele Parrinello

The estimation of the probability of rare events is an important task in reliability and risk assessment. We consider failure events that are expressed in terms of a limit state function, which depends on the solution of a partial…

Numerical Analysis · Mathematics 2020-07-15 Fabian Wagner , Jonas Latz , Iason Papaioannou , Elisabeth Ullmann

Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited utility in practical situations. A more…

Machine Learning · Computer Science 2021-10-28 Ryan R. Strauss , Junier B. Oliva

Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and…

Robotics · Computer Science 2024-03-07 Zhaorun Chen , Zhuokai Zhao , Tairan He , Binhao Chen , Xuhao Zhao , Liang Gong , Chengliang Liu

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

Robotics · Computer Science 2016-09-13 Yunpeng Pan , Xinyan Yan , Evangelos Theodorou , Byron Boots

We address the problem of sequentially selecting and observing processes from a given set to find the anomalies among them. The decision-maker observes one process at a time and obtains a noisy binary indicator of whether or not the…

Machine Learning · Computer Science 2021-05-14 Geethu Joseph , M. Cenk Gursoy , Pramod K. Varshney

Chance-constrained optimization is a suitable modeling framework for safety-critical applications where violating constraints is nearly unacceptable. The scenario approach is a popular solution method for these problems, due to its…

Optimization and Control · Mathematics 2026-03-19 Jaeseok Choi , Anand Deo , Constantino Lagoa , Anirudh Subramanyam

Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the problem of evaluating a new policy using the historical data…

Machine Learning · Computer Science 2020-04-02 Tengyang Xie , Yifei Ma , Yu-Xiang Wang
‹ Prev 1 2 3 10 Next ›