English
Related papers

Related papers: PhiBE: A PDE-based Bellman Equation for Continuous…

200 papers

We present a random measure approach for modeling exploration, i.e., the execution of measure-valued controls, in continuous-time reinforcement learning (RL) with controlled diffusion and jumps. First, we consider the case when sampling the…

Machine Learning · Computer Science 2024-09-27 Christian Bender , Nguyen Tran Thuan

In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…

Machine Learning · Computer Science 2019-11-26 Alex Irpan , Kanishka Rao , Konstantinos Bousmalis , Chris Harris , Julian Ibarz , Sergey Levine

We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments, without requiring the execution of the new policy. This finds important applications in areas…

Machine Learning · Computer Science 2020-08-18 Yihao Feng , Tongzheng Ren , Ziyang Tang , Qiang Liu

In temporal difference (TD) learning, off-policy sampling is known to be more practical than on-policy sampling, and by decoupling learning from data collection, it enables data reuse. It is known that policy evaluation (including…

Machine Learning · Computer Science 2021-06-25 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Machine Learning · Computer Science 2020-12-29 Shuang Li , Shuai Xiao , Shixiang Zhu , Nan Du , Yao Xie , Le Song

H{\infty} control of nonlinear continuous-time system depends on the solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which has been proved impossible to obtain a closed-form solution due to the nonlinearity of HJI equation. In order…

Systems and Control · Electrical Eng. & Systems 2024-03-20 Qi Wang

We present a nonlinear dynamical approximation method for time-dependent Partial Differential Equations (PDEs). The approach makes use of parametrized decoder functions, and provides a general, and principled way of understanding and…

Numerical Analysis · Mathematics 2025-05-20 Daan Bon , Benjamin Caris , Olga Mula

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

Considering generating samples with high rewards, we focus on optimizing deep neural networks parameterized stochastic differential equations (SDEs), the advanced generative models with high expressiveness, with policy gradient, the leading…

Machine Learning · Computer Science 2024-06-27 Xiangxin Zhou , Liang Wang , Yichi Zhou

This paper presents a new formulation for model-free robust optimal regulation of continuous-time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP),…

Systems and Control · Electrical Eng. & Systems 2022-03-25 Cong Li , Yongchao Wang , Fangzhou Liu , Qingchen Liu , Martin Buss

In reinforcement learning, off-policy evaluation (OPE) is the problem of estimating the expected return of an evaluation policy given a fixed dataset that was collected by running one or more different policies. One of the more empirically…

Machine Learning · Computer Science 2023-10-31 Brahma S. Pavse , Josiah P. Hanna

The problem of system identification for the Kalman filter, relying on the expectation-maximization (EM) procedure to learn the underlying parameters of a dynamical system, has largely been studied assuming that observations are sampled at…

Machine Learning · Computer Science 2024-06-28 Peter Halmos , Jonathan Pillow , David A. Knowles

Consider the problem of approximating the optimal policy of a Markov decision process (MDP) by sampling state transitions. In contrast to existing reinforcement learning methods that are based on successive approximations to the nonlinear…

Machine Learning · Computer Science 2017-10-18 Mengdi Wang

We present a formalisation of finite Markov decision processes with rewards in the Isabelle theorem prover. We focus on the foundations required for dynamic programming and the use of reinforcement learning agents over such processes. In…

Logic in Computer Science · Computer Science 2021-12-14 Mark Chevallier , Jacques Fleuriot

One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To…

Machine Learning · Computer Science 2024-06-19 Noah Golowich , Ankur Moitra

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…

Machine Learning · Computer Science 2023-05-16 Adithya Ramesh , Balaraman Ravindran

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…

Systems and Control · Electrical Eng. & Systems 2025-03-20 Dongdong Li , Jiuxiang Dong

We present a physics-informed machine learning (PIML) scheme for the feedback linearization of nonlinear discrete-time dynamical systems. The PIML finds the nonlinear transformation law, thus ensuring stability via pole placement, in one…

One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The…

Machine Learning · Computer Science 2022-07-12 Jakub Łyskawa , Paweł Wawrzyński

A system of dynamically consistent nonlinear evaluation (${\cal{F}}$-evaluation) provides an ideal characterization for the dynamical behaviors of risk measures and the pricing of contingent claims. The purpose of this paper is to study the…

Probability · Mathematics 2016-07-21 Shiqiu Zheng , Shoumei Li
‹ Prev 1 3 4 5 6 7 10 Next ›