English
Related papers

Related papers: Bellman Value Decomposition for Task Logic in Safe…

200 papers

We study stochastic minimum-cost reach-avoid reinforcement learning, where an agent must satisfy a reach-avoid specification with probability at least $p$ while minimizing expected cumulative costs in stochastic environments. Existing safe…

Machine Learning · Computer Science 2026-05-19 Jingduo Pan , Taoran Wu , Yiling Xue , Bai Xue

Time-consistency is an essential requirement in risk sensitive optimal control problems to make rational decisions. An optimization problem is time consistent if its solution policy does not depend on the time sequence of solving the…

Optimization and Control · Mathematics 2015-03-26 Yinlam Chow , Marco Pavone

Some approaches to solving challenging dynamic programming problems, such as Q-learning, begin by transforming the Bellman equation into an alternative functional equation, in order to open up a new line of attack. Our paper studies this…

Optimization and Control · Mathematics 2019-12-05 Qingyin Ma , John Stachurski

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the language model policy to…

Machine Learning · Computer Science 2024-10-22 Akifumi Wachi , Thien Q. Tran , Rei Sato , Takumi Tanabe , Youhei Akimoto

We describe an approximate dynamic programming approach to compute lower bounds on the optimal value function for a discrete time, continuous space, infinite horizon setting. The approach iteratively constructs a family of lower bounding…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Paul N. Beuchat , Joseph Warrington , John Lygeros

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the…

Machine Learning · Computer Science 2025-03-25 Juntao Dai , Taiye Chen , Yaodong Yang , Qian Zheng , Gang Pan

We study the problem of computing the value function from a discretely-observed trajectory of a continuous-time diffusion process. We develop a new class of algorithms based on easily implementable numerical schemes that are compatible with…

Machine Learning · Computer Science 2024-07-09 Wenlong Mou , Yuhua Zhu

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function approximation. Many…

Machine Learning · Computer Science 2024-08-02 Andrew Patterson , Adam White , Martha White

Finding the minimal structural assumptions that empower sample-efficient learning is one of the most important research directions in Reinforcement Learning (RL). This paper advances our understanding of this fundamental question by…

Machine Learning · Computer Science 2021-07-19 Chi Jin , Qinghua Liu , Sobhan Miryoosefi

In this paper we consider a broad class of infinite horizon discrete-time optimal control models that involve a nonnegative cost function and an affine mapping in their dynamic programming equation. They include as special cases classical…

Optimization and Control · Mathematics 2017-11-29 Dimitri Bertsekas

A Task Decomposition method for iterative learning Model Predictive Control (TDMPC) for linear time-varying systems is presented. We consider the availability of state-input trajectories which solve an original task T1, and design a…

Systems and Control · Electrical Eng. & Systems 2020-05-05 Charlott Vallon , Francesco Borrelli

Making optimal decisions under uncertainty is a shared problem among distinct fields. While optimal control is commonly studied in the framework of dynamic programming, it is approached with differing perspectives of the Bellman optimality…

Systems and Control · Electrical Eng. & Systems 2025-03-18 Thomas Banker , Nathan P. Lawrence , Ali Mesbah

We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility involves a certainty equivalent (CE) of…

General Finance · Quantitative Finance 2026-03-25 Minkey Chang

In this paper we consider long-run risk sensitive average cost impulse control applied to a continuous-time Feller-Markov process. Using the probabilistic approach, we show how to get a solution to a suitable continuous-time Bellman…

Optimization and Control · Mathematics 2021-04-01 Damian Jelito , Marcin Pitera , Łukasz Stettner

In energy management, it is common that strategic investment decisions (storage capacity, production units) are made at a slow time scale, whereas operational decisions (storage, production) are made at a fast time scale: for such problems,…

Optimization and Control · Mathematics 2023-03-08 Tristan Rigaut , Pierre Carpentier , Jean-Philippe Chancelier , Michel de Lara

Discrete time stochastic optimal control problems and Markov decision processes (MDPs), respectively, serve as fundamental models for problems that involve sequential decision making under uncertainty and as such constitute the theoretical…

Optimization and Control · Mathematics 2023-03-08 Christian Beck , Arnulf Jentzen , Konrad Kleinberg , Thomas Kruse

The solutions to many sequential decision-making problems are characterized by dynamic programming and Bellman's principle of optimality. However, due to the inherent complexity of solving Bellman's equation exactly, there has been…

Systems and Control · Electrical Eng. & Systems 2026-03-24 Bowen Li , Edwin K. P. Chong , Ali Pezeshki

When sales of a product are affected by randomness in demand, retailers can use dynamic pricing strategies to maximise their profits. In this article the pricing problem is formulated as a stochastic optimal control problem, where the…

Optimization and Control · Mathematics 2017-10-17 Asbjørn N. Riseth , Jeff N. Dewynne , Chris L. Farmer

As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning…

Robotics · Computer Science 2026-02-16 Xinhuan Sang , Abdelrahman Abdelgawad , Roberto Tron

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…

Computation and Language · Computer Science 2026-03-04 Yueyang Cang , Xiaoteng Zhang , Erlu Zhao , Zehua Ji , Yuhang Liu , Yuchen He , Zhiyuan Ning , Chen Yijun , Wenge Que , Li Shi