English
Related papers

Related papers: Behavior-Induced Mirror-Prox Temporal-Difference L…

200 papers

We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a…

Optimization and Control · Mathematics 2015-09-10 Yuchen Zhang , Lin Xiao

Saddle-point or primal-dual methods have recently attracted renewed interest as a systematic technique to design distributed algorithms which solve convex optimization problems. When implemented online for streaming data or as dynamic…

Optimization and Control · Mathematics 2021-04-22 John W. Simpson-Porco , Bala Kameshwar Poolla , Nima Monshizadeh , Florian Dorfler

Explicit exploration in the action space was assumed to be indispensable for online policy gradient methods to avoid a drastic degradation in sample complexity, for solving general reinforcement learning problems over finite state and…

Machine Learning · Computer Science 2023-03-22 Yan Li , Guanghui Lan

We provide theoretical guarantees for convergence of discrete-time policy mirror descent with inexact advantage functions updated using temporal difference (TD) learning for entropy regularised MDPs in Polish state and action spaces. We…

Optimization and Control · Mathematics 2026-02-12 Denis Zorba , David Šiška , Lukasz Szpruch

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Machine Learning · Computer Science 2020-05-19 Mingde Zhao , Sitao Luan , Ian Porada , Xiao-Wen Chang , Doina Precup

Performative prediction (PP) is an algorithmic framework for optimizing machine learning (ML) models where the model's deployment affects the distribution of the data it is trained on. Compared to traditional ML with fixed data, designing…

Machine Learning · Computer Science 2025-09-24 Tian Xie , Ding Zhu , Jia Liu , Mahdi Khalili , Xueru Zhang

Due to simplicity and strong stability guarantees, predictor feedback methods have stood as a popular approach for time delay systems since the 1950s. For time-varying delays, however, implementation requires computing a prediction horizon…

Systems and Control · Electrical Eng. & Systems 2026-04-01 Luke Bhan , Miroslav Krstic , Yuanyuan Shi

Recent work has considered trust-aware decision making for human-robot collaboration (HRC) with a focus on model learning. In this paper, we are interested in enabling the HRC system to complete complex tasks specified using temporal logic…

Robotics · Computer Science 2023-10-03 Pian Yu , Shuyang Dong , Shili Sheng , Lu Feng , Marta Kwiatkowska

In this paper, we derive a randomized version of the Mirror-Prox method for solving some structured matrix saddle-point problems, such as the maximal eigenvalue minimization problem. Deterministic first-order schemes, such as Nesterov's…

Optimization and Control · Mathematics 2011-12-07 Michel Baes , Michael Bürgisser , Arkadi Nemirovski

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 study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice…

Machine Learning · Computer Science 2024-09-20 Gandharv Patil , Prashanth L. A. , Dheeraj Nagaraj , Doina Precup

Diffusion models are increasingly used for robot learning, but current designs face a clear trade-off. Action-chunking diffusion policies like ManiCM are fast to run, yet they only predict short segments of motion. This makes them reactive,…

Robotics · Computer Science 2026-03-27 Xirui Shi , Arya Ebrahimi , Yi Hu , Jun Jin

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

Machine Learning · Computer Science 2016-07-18 William Montgomery , Sergey Levine

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To…

Machine Learning · Computer Science 2018-11-27 Huizhen Yu , A. Rupam Mahmood , Richard S. Sutton

The primal dual hybrid gradient algorithm (PDHG), which is also known as the Arrow-Hurwicz method, is a fundamental algorithm for saddle point problems especially in imaging. It also inspires a great number of influential algorithms such as…

Optimization and Control · Mathematics 2026-03-03 Shengjie Xu , Bingsheng He

We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle…

Machine Learning · Statistics 2015-06-15 Zhanxing Zhu , Amos J. Storkey

Dynamic Movement Primitives (DMP) are an established and efficient method for encoding robotic tasks that require adaptation based on reference motions. Typically, the nominal trajectory is obtained through Programming by Demonstration…

Robotics · Computer Science 2025-07-23 Giovanni Braglia , Davide Tebaldi , Luigi Biagiotti

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…

Machine Learning · Computer Science 2026-04-08 Masoud S. Sakha , Rushikesh Kamalapurkar , Sean Meyn

Forecasting human trajectories in traffic scenes is critical for safety within mixed or fully autonomous systems. Human future trajectories are driven by two major stimuli, social interactions, and stochastic goals. Thus, reliable…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Chen Zhou , Ghassan AlRegib , Armin Parchami , Kunjan Singh

Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we…

Machine Learning · Computer Science 2025-02-07 Haotian Lin , Pengcheng Wang , Jeff Schneider , Guanya Shi