English
Related papers

Related papers: Formal Methods with a Touch of Magic

200 papers

Deep reinforcement learning has led to several recent breakthroughs, though the learned policies are often based on black-box neural networks. This makes them difficult to interpret and to impose desired specification constraints during…

Machine Learning · Computer Science 2018-07-05 Surya Bhupatiraju , Kumar Krishna Agrawal , Rishabh Singh

Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several…

Extensive research on formal verification of machine learning (ML) systems indicates that learning from data alone often fails to capture underlying background knowledge. A variety of verifiers have been developed to ensure that a…

Logic in Computer Science · Computer Science 2023-11-17 Thomas Flinkow , Barak A. Pearlmutter , Rosemary Monahan

Black-box optimization (BBO) addresses problems where objectives are accessible only through costly queries without gradients or explicit structure. Classical derivative-free methods -- line search, direct search, and model-based solvers…

Machine Learning · Computer Science 2025-10-01 Morteza Kimiaei , Vyacheslav Kungurtsev

The stochastic control problem of optimal market making is among the central problems in quantitative finance. In this paper, a deep reinforcement learning-based controller is trained on a weakly consistent, multivariate Hawkes…

General Finance · Quantitative Finance 2022-07-21 Bruno Gašperov , Zvonko Kostanjčar

Deep Reinforcement Learning (DRL) has demonstrated promising capability in solving complex control problems. However, DRL applications in safety-critical systems are hindered by the inherent lack of robust verification techniques to assure…

Machine Learning · Computer Science 2023-10-10 Amir Samadi , Konstantinos Koufos , Kurt Debattista , Mehrdad Dianati

We consider the problem of designing an algorithm to allow a car to autonomously merge on to a highway from an on-ramp. Two broad classes of techniques have been proposed to solve motion planning problems in autonomous driving: Model…

Robotics · Computer Science 2021-09-29 Joseph Lubars , Harsh Gupta , Sandeep Chinchali , Liyun Li , Adnan Raja , R. Srikant , Xinzhou Wu

We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on large-scale…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Dongdong Wang , Yandong Li , Liqiang Wang , Boqing Gong

The combination of deep neural nets and theory-driven models, which we call deep grey-box modeling, can be inherently interpretable to some extent thanks to the theory backbone. Deep grey-box models are usually learned with a regularized…

Machine Learning · Computer Science 2022-10-25 Naoya Takeishi , Alexandros Kalousis

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. To analyze reasoning dynamics, we use synthetic logic puzzles as training data due to their controllable…

Computation and Language · Computer Science 2025-02-21 Tian Xie , Zitian Gao , Qingnan Ren , Haoming Luo , Yuqian Hong , Bryan Dai , Joey Zhou , Kai Qiu , Zhirong Wu , Chong Luo

In recent times, reinforcement learning has produced baffling results when it comes to performing control tasks with highly non-linear systems. The impressive results always outweigh the potential vulnerabilities or uncertainties associated…

Robotics · Computer Science 2023-11-14 Arshad Javeed

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on…

Machine Learning · Computer Science 2019-05-15 Richard Cheng , Abhinav Verma , Gabor Orosz , Swarat Chaudhuri , Yisong Yue , Joel W. Burdick

Engineering desired Hamiltonian in quantum many-body systems is essential for applications such as quantum simulation, computation and sensing. Conventional quantum Hamiltonian engineering sequences are designed using human intuition based…

Quantum Physics · Physics 2022-11-17 Pai Peng , Xiaoyang Huang , Chao Yin , Linta Joseph , Chandrasekhar Ramanathan , Paola Cappellaro

Developing an automated driving system capable of navigating complex traffic environments remains a formidable challenge. Unlike rule-based or supervised learning-based methods, Deep Reinforcement Learning (DRL) based controllers eliminate…

Machine Learning · Computer Science 2025-01-28 Zhihao Zhang , Ekim Yurtsever , Keith A. Redmill

In recent years some researchers have explored the use of reinforcement learning (RL) algorithms as key components in the solution of various natural language processing tasks. For instance, some of these algorithms leveraging deep neural…

Computation and Language · Computer Science 2026-04-29 Victor Uc-Cetina , Nicolas Navarro-Guerrero , Anabel Martin-Gonzalez , Cornelius Weber , Stefan Wermter

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

Machine Learning · Computer Science 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine

This paper presents an approach for learning Model Predictive Control (MPC) schemes directly from data using Reinforcement Learning (RL) methods. The state-of-the-art learning methods use RL to improve the performance of parameterized MPC…

Systems and Control · Electrical Eng. & Systems 2023-01-05 Shambhuraj Sawant , Akhil S Anand , Dirk Reinhardt , Sebastien Gros

Algorithmic trading requires short-term tactical decisions consistent with long-term financial objectives. Reinforcement Learning (RL) has been applied to such problems, but adoption is limited by myopic behaviour and opaque policies. Large…

Machine Learning · Computer Science 2025-10-28 Adam Darmanin , Vince Vella

Reinforcement learning and classical planning are typically seen as two distinct problems, with differing formulations necessitating different solutions. Yet, when humans are given a task, regardless of the way it is specified, they can…

Machine Learning · Computer Science 2026-02-10 Gabriel Stella
‹ Prev 1 4 5 6 7 8 10 Next ›