English
Related papers

Related papers: Connected Superlevel Set in (Deep) Reinforcement L…

200 papers

We offer a theoretical characterization of off-policy evaluation (OPE) in reinforcement learning using function approximation for marginal importance weights and $q$-functions when these are estimated using recent minimax methods. Under…

Machine Learning · Computer Science 2022-07-26 Masatoshi Uehara , Masaaki Imaizumi , Nan Jiang , Nathan Kallus , Wen Sun , Tengyang Xie

Reinforcement learning aims to learn optimal policies from interaction with environments whose dynamics are unknown. Many methods rely on the approximation of a value function to derive near-optimal policies. In partially observable…

Machine Learning · Computer Science 2022-09-13 Gaspard Lambrechts , Adrien Bolland , Damien Ernst

Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for function approximations when facing large state-action spaces.…

Machine Learning · Computer Science 2025-11-03 Zhishuai Liu , Pan Xu

Teaming is the process of establishing connections among agents within a system to enable collaboration toward achieving a collective goal. This paper examines teaming in the context of a network of agents learning to coordinate with…

Systems and Control · Electrical Eng. & Systems 2025-04-08 Zhewei Wang , Olugbenga Moses Anubi , Marcos M. Vasconcelos

Despite the rich existing literature about minimax optimization in continuous settings, only very partial results of this kind have been obtained for combinatorial settings. In this paper, we fill this gap by providing a characterization of…

Machine Learning · Computer Science 2023-05-29 Loay Mualem , Ethan R. Elenberg , Moran Feldman , Amin Karbasi

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

In a multirobot system, a number of cyber-physical attacks (e.g., communication hijack, observation perturbations) can challenge the robustness of agents. This robustness issue worsens in multiagent reinforcement learning because there…

Machine Learning · Computer Science 2021-09-15 Chuangchuang Sun , Dong-Ki Kim , Jonathan P. How

We study a class of bilevel convex optimization problems where the goal is to find the minimizer of an objective function in the upper level, among the set of all optimal solutions of an optimization problem in the lower level. A wide range…

Optimization and Control · Mathematics 2018-09-27 Mostafa Amini , Farzad Yousefian

We study the problem of representation learning in goal-conditioned hierarchical reinforcement learning. In such hierarchical structures, a higher-level controller solves tasks by iteratively communicating goals which a lower-level policy…

Artificial Intelligence · Computer Science 2019-01-10 Ofir Nachum , Shixiang Gu , Honglak Lee , Sergey Levine

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate this problem of finding an allocation policy within a…

Artificial Intelligence · Computer Science 2020-12-23 Nymisha Bandi , Theja Tulabandhula

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

We study the problem of joint optimization involving coding and control policies for a controlled Markovian sytem over a finite-rate noiseless communication channel. While structural results on the optimal encoding and control have been…

Optimization and Control · Mathematics 2026-03-18 Evelyn Hubbard , Liam Cregg , Serdar Yüksel

Learning the optimized solution as a function of environmental parameters is effective in solving numerical optimization in real time for time-sensitive applications. Existing works of learning to optimize train deep neural networks (DNN)…

Machine Learning · Computer Science 2019-05-28 Chengjian Sun , Chenyang Yang

We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad class of objectives built on a…

Computational Finance · Quantitative Finance 2026-03-09 Chang Chen , Duy-Minh Dang

As distributed learning applications such as Federated Learning, the Internet of Things (IoT), and Edge Computing grow, it is critical to address the shortcomings of such technologies from a theoretical perspective. As an abstraction, we…

Machine Learning · Computer Science 2025-03-14 Sajjad Ghiasvand , Amirhossein Reisizadeh , Mahnoosh Alizadeh , Ramtin Pedarsani

Stochastic resetting, where a dynamical process is intermittently returned to a fixed reference state, has emerged as a powerful mechanism for optimizing first-passage properties. Existing theory largely treats static, non-learning…

Machine Learning · Computer Science 2026-03-18 Jello Zhou , Vudtiwat Ngampruetikorn , David J. Schwab

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine Learning · Computer Science 2024-03-19 Jan Schneider , Pierre Schumacher , Simon Guist , Le Chen , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

Regularized empirical risk minimization with constrained labels (in contrast to fixed labels) is a remarkably general abstraction of learning. For common loss and regularization functions, this optimization problem assumes the form of a…

Machine Learning · Computer Science 2016-02-23 Iaroslav Shcherbatyi , Bjoern Andres

Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this paper, we draw connections between DP and (constrained)…

Machine Learning · Computer Science 2019-10-30 Nino Vieillard , Olivier Pietquin , Matthieu Geist