English
Related papers

Related papers: Unifying Entropy Regularization in Optimal Control…

200 papers

We propose and analyse a class of analytically solvable models of quantum reinforcement learning (QRL), formulated as finite-horizon Markov decision processes in finite-dimensional Hilbert spaces. The models are built around a…

General Mathematics · Mathematics 2026-04-16 Andrea Cintio , Alessandro Michelangeli , Dmitrii Tsutskov

Derivative based optimization methods are efficient at solving optimal control problems near local optima. However, their ability to converge halts when derivative information vanishes. The inference approach to optimal control does not…

Robotics · Computer Science 2022-03-01 Daniel Layeghi , Steve Tonneau , Michael Mistry

This paper proposes and analyzes two new policy learning methods: regularized policy gradient (RPG) and iterative policy optimization (IPO), for a class of discounted linear-quadratic control (LQC) problems over an infinite time horizon…

Optimization and Control · Mathematics 2025-10-08 Xin Guo , Xinyu Li , Renyuan Xu

In this short expository note, we describe a unified algorithmic perspective on several classical problems which have traditionally been studied in different communities. This perspective views the main characters -- the problems of Optimal…

Optimization and Control · Mathematics 2022-11-01 Jason M. Altschuler

The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast…

Machine Learning · Computer Science 2021-04-15 Moritz A. Zanger , Karam Daaboul , J. Marius Zöllner

Sample-based trajectory optimisers are a promising tool for the control of robotics with non-differentiable dynamics and cost functions. Contemporary approaches derive from a restricted subclass of stochastic optimal control where the…

Robotics · Computer Science 2021-10-07 Tom Lefebvre , Guillaume Crevecoeur

Reinforcement learning (RL) and trajectory optimization (TO) present strong complementary advantages. On one hand, RL approaches are able to learn global control policies directly from data, but generally require large sample sizes to…

Robotics · Computer Science 2023-02-17 Quentin Le Lidec , Wilson Jallet , Ivan Laptev , Cordelia Schmid , Justin Carpentier

Soft robots were introduced in large part to enable safe, adaptive interaction with the environment, and this interaction relies fundamentally on contact. However, modeling and planning contact-rich interactions for soft robots remain…

Robotics · Computer Science 2026-02-26 Milad Azizkhani , Yue Chen

We investigate an entropy-regularized reinforcement learning (RL) approach to optimal stopping problems motivated by real option models. Classical stopping rules are strict and non-randomized, limiting natural exploration in RL settings. To…

Optimization and Control · Mathematics 2026-02-18 Jodi Dianetti , Giorgio Ferrari , Renyuan Xu

This paper presents a unified derivation of transversality conditions in optimal control problems using exact penalty functions. The key regularity condition is that the origin is uniformly separated from the subdifferential of the penalty…

Optimization and Control · Mathematics 2026-05-04 Majid Abbasov

For a general entropy-regularized stochastic control problem on an infinite horizon, we prove that a policy iteration algorithm (PIA) converges to an optimal relaxed control. Contrary to the standard stochastic control literature, classical…

Optimization and Control · Mathematics 2026-05-14 Yu-Jui Huang , Zhenhua Wang , Zhou Zhou

Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy. The primary motivation for…

Machine Learning · Computer Science 2021-01-19 Hisham Husain , Kamil Ciosek , Ryota Tomioka

We describe an algorithm to solve Bellman optimization that replaces a sum over paths determining the optimal cost-to-go by an analytic method localized in state space. Our approach follows from the established relation between stochastic…

Optimization and Control · Mathematics 2022-12-02 Michael D. Schneider , Caleb Miller , George F. Chapline , Jane Pratt , Dan Merl

Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes…

Machine Learning · Computer Science 2019-06-05 Matthieu Geist , Bruno Scherrer , Olivier Pietquin

Stochastic Optimal Control (SOC) problems arise in systems influenced by uncertainty, such as autonomous robots or financial models. Traditional methods like dynamic programming are often intractable for high-dimensional, nonlinear systems…

Optimization and Control · Mathematics 2025-04-25 Apurva Patil

We develop a mathematical theory of entropic regularisation of unbalanced optimal transport problems. Focusing on static formulation and relying on the formalism developed for the unregularised case, we show that unbalanced optimal…

Optimization and Control · Mathematics 2023-05-05 Maciej Buze , Manh Hong Duong

This paper revisits a classical challenge in the design of stabilizing controllers for nonlinear systems with a norm-bounded input constraint. By extending Lin-Sontag's universal formula and introducing a generic (state-dependent) scaling…

Systems and Control · Electrical Eng. & Systems 2026-04-22 Ming Li , Zhiyong Sun , Siep Weiland

Recent work has led to the development of an elegant theory of Linearly Solvable Markov Decision Processes (LMDPs) and related Path-Integral Control Problems. Traditionally, MDPs have been formulated using stochastic policies and a control…

Systems and Control · Computer Science 2012-02-20 Krishnamurthy Dvijotham , Emanuel Todorov

This paper explores continuous-time and state-space optimal stopping problems from a reinforcement learning perspective. We begin by formulating the stopping problem using randomized stopping times, where the decision maker's control is…

Optimization and Control · Mathematics 2026-03-12 Jodi Dianetti , Giorgio Ferrari , Renyuan Xu

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu