English
Related papers

Related papers: Distributionally Robust Deep Q-Learning

200 papers

Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is…

Machine Learning · Statistics 2020-03-24 Johannes Kirschner , Ilija Bogunovic , Stefanie Jegelka , Andreas Krause

Recent work have shown how the optimal state-feedback, obtained as the solution to the Hamilton-Jacobi-Bellman equations, can be approximated for several nonlinear, deterministic systems by deep neural networks. When imitation (supervised)…

Neural and Evolutionary Computing · Computer Science 2019-04-02 Dario Izzo , Dharmesh Tailor , Thomas Vasileiou

Offline reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However, most methods assume all…

Machine Learning · Statistics 2025-10-30 David Bruns-Smith , Angela Zhou

A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. Verification approaches centered around reachability analysis fail to scale, and purely statistical approaches…

Artificial Intelligence · Computer Science 2025-03-11 Souradeep Dutta , Michele Caprio , Vivian Lin , Matthew Cleaveland , Kuk Jin Jang , Ivan Ruchkin , Oleg Sokolsky , Insup Lee

We propose a diffusion approximation method to the continuous-state Markov Decision Processes (MDPs) that can be utilized to address autonomous navigation and control in unstructured off-road environments. In contrast to most…

Robotics · Computer Science 2024-02-08 Junhong Xu , Kai Yin , Zheng Chen , Jason M. Gregory , Ethan A. Stump , Lantao Liu

Designing model-free algorithms for distributionally robust reinforcement learning (DRRL) poses fundamental challenges. The robust Bellman operator is nonlinear in the transition kernel, which makes one-sample Bellman updates biased, while…

Machine Learning · Computer Science 2026-05-12 Shengbo Wang , Zexi Zhang

This paper proposes a novel approach to construct data-driven online solutions to optimization problems (P) subject to a class of distributionally uncertain dynamical systems. The introduced framework allows for the simultaneous learning of…

Systems and Control · Electrical Eng. & Systems 2024-07-23 Dan Li , Dariush Fooladivanda , Sonia Martinez

The design and testing of supervised machine learning models combine two fundamental distributions: (1) the training data distribution (2) the testing data distribution. Although these two distributions are identical and identifiable when…

Machine Learning · Computer Science 2021-03-19 Peyman Tavallali , Hamed Hamze Bajgiran , Danial J. Esaid , Houman Owhadi

We study the offline data-driven sequential decision making problem in the framework of Markov decision process (MDP). In order to enhance the generalizability and adaptivity of the learned policy, we propose to evaluate each policy by a…

Statistics Theory · Mathematics 2021-11-11 Zhengling Qi , Peng Liao

We present a case study applying learning-based distributionally robust model predictive control to highway motion planning under stochastic uncertainty of the lane change behavior of surrounding road users. The dynamics of road users are…

Systems and Control · Electrical Eng. & Systems 2022-11-08 Mathijs Schuurmans , Alexander Katriniok , Christopher Meissen , H. Eric Tseng , Panagiotis Patrinos

This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…

Systems and Control · Electrical Eng. & Systems 2023-04-03 Victor G. Lopez , Mohammad Alsalti , Matthias A. Müller

In this paper we explore the relation between distributionally robust learning and different forms of regularization to enforce robustness of deep neural networks. In particular, starting from a concrete min-max distributionally robust…

Optimization and Control · Mathematics 2022-03-29 Camilo Garcia Trillos , Nicolas Garcia Trillos

This paper studies the problem of steering the distribution of a discrete-time dynamical system from an initial distribution to a target distribution in finite time. The formulation is fully nonlinear, allowing the use of general control…

Systems and Control · Electrical Eng. & Systems 2024-09-05 George Rapakoulias , Panagiotis Tsiotras

We investigate the challenges of applying model-free reinforcement learning algorithms, like online Q-learning, to infinite state space Markov Decision Processes (MDPs). We first introduce the notion of Local Learning Processes (LLPs),…

Probability · Mathematics 2025-11-03 Urtzi Ayesta , Sergey Foss , Matthieu Jonckheere , Vittorio Puricelli

A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method. Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are achieved by the…

Machine Learning · Computer Science 2026-05-22 D. Sorokin , A. Kostin , L. Savchenko , G. Gusev , A. V. Savchenko

We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-art methods that estimate the distribution, as opposed to only…

Machine Learning · Computer Science 2020-12-10 Thanh Tang Nguyen , Sunil Gupta , Svetha Venkatesh

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with…

Machine Learning · Computer Science 2022-01-03 Tien Mai , Patrick Jaillet

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited…

Machine Learning · Computer Science 2024-09-06 Narim Jeong , Donghwan Lee

Sequential fine-tuning of transformers is useful when new data arrive sequentially, especially with shifting distributions. Unlike batch learning, sequential learning demands that training be stabilized despite a small amount of data by…

Machine Learning · Computer Science 2025-09-16 Haoming Jing , Oren Wright , José M. F. Moura , Yorie Nakahira

Non-stationary environments pose a fundamental challenge for deep reinforcement learning, as changes in dynamics or rewards invalidate learned value functions and cause catastrophic forgetting. We propose \emph{Gradient-Boosted Deep…

Machine Learning · Computer Science 2025-12-22 Chang-Hwan Lee , Chanseung Lee