arXiv research

Proves robust transitivity for geodesic flows from metrics with conjugate points.

New algorithm reduces performance loss in IRL with mismatched transition dynamics.

New method improves robustness of deep learning with noisy labels.

The paper tackles robust control for insurance contracts under uncertain transition rates.

A new algorithm for deep Q-learning with robustness to state transition uncertainty.

A new method learns robust policies from offline data with latent structures.

Abstract: Nonlinear random walk with distributionally robust transition probabilities.

SCPO learns robust policies without modeling disturbance, improving real-world task performance.

WRAAC uses Wasserstein distance for robust reinforcement learning.

Model improves robustness of neural network sequences without transition failures.

RRPI improves offline RL by optimizing policies against worst-case dynamics.

We define transit clusters to simplify causal diagrams and preserve their essential properties.

This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DR…

The paper explores robustness in linear regression models under adversarial attacks.

Tyler's M-estimator's phase transition at DS-SNR = 1 is resolved.

New algorithms solve robust MDPs efficiently, significantly faster than existing methods.

Safe reinforcement learning framework using optimal transport for robustness.

The paper models market crashes as phase transitions, finding dynamic transitions offer better predictions.

High-dimensional models become unstable when sample size falls below a critical level, leading to a phase transition.

Improves robust transfer learning with side information.

Study online RL with mismatched dynamics, achieving sublinear regret.

In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative f…

Enhances neural network dynamics to boost computational capacity.

DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.

The interaction between transitivity and sparsity, two common features in empirical networks, implies that there are local regions of large sparse networks that are dense. We call this the blessing of transitivity and it has consequences for both modeling and inference. Extant research suggests that statistical inferen…

We develop efficient and sharp bounds on policy value under perturbations in MDPs.

Novel framework for risk-sensitive reinforcement learning with robustness against uncertainty.

Persistent entropy detects phase transitions in complex systems.

We present a novel kernel-based machine learning algorithm for identifying the low-dimensional geometry of the effective dynamics of high-dimensional multiscale stochastic systems. Recently, the authors developed a mathematical framework for the computation of optimal reaction coordinates of such systems that is based …

This study tackles adversarial corruption in model-based reinforcement learning.

The stability of money value is an important requisite for a functioning economy, yet it critically depends on the actions of participants in the market themselves. Here we model the value of money as a dynamical variable that results from trading between agents. The basic trading scenario can be recast into an Ising t…

We propose a principled algorithm for robust Bayesian filtering and smoothing in nonlinear stochastic dynamic systems when both the transition function and the measurement function are described by non-parametric Gaussian process (GP) models. GPs are gaining increasing importance in signal processing, machine learning,…

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …

A Robust Markov Decision Process (RMDP) is a sequential decision making model that accounts for uncertainty in the parameters of dynamic systems. This uncertainty introduces difficulties in learning an optimal policy, especially for environments with large state spaces. We propose two algorithms, RTD-DQN and Deep-RoK, …

A new framework for robust policy learning in MDPs with linear mixture dynamics.

New algorithm solves uncertain Markov decision processes using Wasserstein uncertainty.

Bayesian method infers transition matrices from incomplete graph data with topological constraints.

Robust Markov Decision Processes (RMDPs) intend to ensure robustness with respect to changing or adversarial system behavior. In this framework, transitions are modeled as arbitrary elements of a known and properly structured uncertainty set and a robust optimal policy can be derived under the worst-case scenario. In t…

A framework combining HSMM and survival analysis for lifecycle-oriented mobility analysis.

FourNet approximates financial transition densities using Fourier transforms.

Paper develops a robust classifier for Gaussian mixture models under sparse adversarial perturbations.

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth labels by an unknown noise transition matrix. Thus, by estimating this matrix, classifiers can escape from overfitting those noisy labels. …

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm call…

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. E…

The paper tackles joint learning of linear systems, improving accuracy with pooled data.

The paper uses machine learning and Lie groups to improve rating transitions and XVA calculations.

State entropy regularization improves robustness in reinforcement learning, especially under structured perturbations.

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.