arXiv research

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

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for safely learning a control strategy for a given system with an additive disturba…

MFRL-BI controls manufacturing processes without needing accurate models.

EGFC learns from streaming data to classify power quality disturbances.

New approach generates optimal disturbances for controller verification.

The paper analyzes how disturbances affect the convergence of algorithms in complex systems.

Identifying the location of a disturbance and its magnitude is an important component for stable operation of power systems. We study the problem of localizing and estimating a disturbance in the interconnected power system. We take a model-free approach to this problem by using frequency data from generators. Specific…

New method uses neural nets to control systems safely with disturbances.

Optimistic Q-learning reduces sample complexity for systems with known dynamics.

Study examines how disturbances affect financial returns in Austrian forests.

Paper develops online learning-based risk-averse MPC for uncertain systems.

Paper revisits set membership estimation for linear systems with relaxed disturbance bounds.

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result…

Deep models predict intraday electricity prices accurately.

Power quality (PQ) analysis describes the non-pure electric signals that are usually present in electric power systems. The automatic recognition of PQ disturbances can be seen as a pattern recognition problem, in which different types of waveform distortion are differentiated based on their features. Similar to other …

New method identifies network dynamics and noise structure.

This paper presents a study on power grid disturbance classification by Deep Learning (DL). A real synchrophasor set composing of three different types of disturbance events from the Frequency Monitoring Network (FNET) is used. An image embedding technique called Gramian Angular Field is applied to transform each time …

Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.

New algorithm achieves logarithmic regret for adversarial online control.

Protocol learns pure quantum states with minimal disturbance.

New method controls linear systems with adversarial disturbances.

Paper proposes tensor-based method for semiconductor manufacturing process control.

New method controls linear systems with partial info and disturbances.

WRAAC uses Wasserstein distance for robust reinforcement learning.

Bayesian method optimizes rescheduling for multipurpose batch processes with incomplete look-ahead information.

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds additional procedure…

A method to minimize regret in multi-agent control systems with adversarial disturbances.

New method recovers causal order from dependent data.

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system…

New method uses small perturbations to improve representation learning from few labels.

Gradient boosting for spatial regression models improves prediction accuracy.

Reinforcement Learning optimizes low-thrust interplanetary trajectories under disturbances.

We propose a new class of models specifically tailored for spatio-temporal data analysis. To this end, we generalize the spatial autoregressive model with autoregressive and heteroskedastic disturbances, i.e. SARAR(1,1), by exploiting the recent advancements in Score Driven (SD) models typically used in time series eco…

Study online control of unknown time-varying systems with negative and positive results.

Develops robust MDPs for unknown disturbances with performance guarantees.

Proves hardness of semi-discrete optimal transport and proposes regularization methods.

We address the information content of European option prices about volatility in terms of the Fisher information matrix. We assume that observed option prices are centred on the theoretical price provided by Heston's model disturbed by additive Gaussian noise. We fit the likelihood function on the components of the VIX…

Paper develops a neural-fuzzy controller for GPS-intelligent buoys.

Improves reinforcement learning policies for robustness.

Paper reduces sample complexity for bilinear systems identification to nearly constant.

In this paper, we utilize information theory to study the fundamental performance limitations of generic feedback systems, where both the controller and the plant may be any causal functions/mappings while the disturbance can be with any distributions. More specifically, we obtain fundamental $\mathcal{L}_p$ bounds on …

New framework boosts neural network performance and resilience.

This work uses QPGPs to improve ILC performance in repetitive tasks.

We propose a series of simple models for the microstructure of a double auction market without intermediaries. We specialize to those markets, such interdealer broker markets, which are dominated by professional traders, who trade mainly through limit orders, watch markets closely, and move their limit order prices fre…

New algorithm optimizes multi-armed bandits with low computational cost.

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity. Risk-sensitive inverse reinforcement learning (RS-IRL) bridges such gap by assum…

We study the regular conditional law of mixed Gaussian Volterra processes under the influence of model disturbances. More precisely, we study prediction of Gaussian Volterra processes driven by a Brownian motion in a case where the Brownian motion is not observable, but only a noisy version is observed. As an applicati…

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal operations. While the control system can compensate for many types of disturban…