arXiv research

New risk control method for non-monotonic losses in complex parameters.

New algorithm achieves logarithmic regret for adversarial online control.

Langevin algorithms enhance training of deep neural networks for stochastic control problems.

New algorithms control FDX while achieving more power in online multiple testing.

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…

Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new algorithm sequentially updates the control policies in each time period using Mo…

Optimizes control of noisy discrete systems without system matrix knowledge.

New algorithm controls systems with unknown, changing losses.

CTRL improves reinforcement learning by combining control strategies.

New RL algorithms improve control tasks with data reuse.

Editorial discusses nine challenges in modern algorithmic trading.

Meta-learning control algorithm with finite-time guarantees for unknown systems.

The OGY method is one of control methods for a chaotic system. In the method, we have to calculate a stabilizing periodic orbit embedded in its chaotic attractor. Thus, we cannot use this method in the case where a precise mathematical model of the chaotic system cannot be identified. In this case, the delayed feedback…

A number of optimal decision problems with uncertainty can be formulated into a stochastic optimal control framework. The Least-Squares Monte Carlo (LSMC) algorithm is a popular numerical method to approach solutions of such stochastic control problems as analytical solutions are not tractable in general. This paper ge…

Two clustering algorithms optimize edge controller placement in wireless networks.

This paper presents several numerical applications of deep learning-based algorithms that have been introduced in [HPBL18]. Numerical and comparative tests using TensorFlow illustrate the performance of our different algorithms, namely control learning by performance iteration (algorithms NNcontPI and ClassifPI), contr…

We study Bayesian optimal control of a general class of smoothly parameterized Markov decision problems. Since computing the optimal control is computationally expensive, we design an algorithm that trades off performance for computational efficiency. The algorithm is a lazy posterior sampling method that maintains a d…

A new ML algorithm solves complex economic control problems.

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

Algorithm reduces control regret for unknown systems.

Automates bias control in reinforcement learning algorithms.

New online learning algorithms improve cyberattack detection in industrial control systems.

Controlled interacting particle systems such as the ensemble Kalman filter (EnKF) and the feedback particle filter (FPF) are numerical algorithms to approximate the solution of the nonlinear filtering problem in continuous time. The distinguishing feature of these algorithms is that the Bayesian update step is implemen…

Differentially private synthetic control estimates treatment effects while protecting privacy.

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.

Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinfor…

In this paper, we propose a decision making algorithm intended for automated vehicles that negotiate with other possibly non-automated vehicles in intersections. The decision algorithm is separated into two parts: a high-level decision module based on reinforcement learning, and a low-level planning module based on mod…

We geometrically describe optimal control problems in terms of Morse families in the Hamiltonian framework. These geometric structures allow us to recover the classical first order necessary conditions for optimality and the starting point to run an integrability algorithm. Moreover the integrability algorithm is adapt…

dtControl uses decision trees to represent controllers efficiently and explainably.

Improved confidence interval estimation with control variates.

Paper proves deep learning method for stochastic control converges and outperforms existing algorithms.

RL models improve target control in SSGs for security applications.

Adaptive traffic control uses deep RL to improve decision-making.

New algorithm uses control variates to improve multi-armed bandit performance.

Extends conformal prediction for controlling expected risk of monotone loss functions.

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

The paper solves complex control problems using neural networks.

This work frames active inference through control as inference, offering robust control algorithms.

Algorithm optimizes system design and control for better rewards.

Paper proposes CARL for better control in RL from sensory data.

Classical methods to control heating systems are often marred by suboptimal performance, inability to adapt to dynamic conditions and unreasonable assumptions e.g. existence of building models. This paper presents a novel deep reinforcement learning algorithm which can control space heating in buildings in a computatio…

New algorithm reduces control error in systems with changing dynamics.

This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic adaptive control and reinforcement learning literature using model-b…

A novel Q-learning algorithm connects information theory to MPC, improving control tasks.

The PC algorithm allows investigators to estimate a complete partially directed acyclic graph (CPDAG) from a finite dataset, but few groups have investigated strategies for estimating and controlling the false discovery rate (FDR) of the edges in the CPDAG. In this paper, we introduce PC with p-values (PC-p), a fast al…

Exploiting capacity of sewer system using decentralized control is a cost effective mean of minimizing the overflow. Given the size of the real sewer system, exploiting all the installed control structures in the sewer pipes can be challenging. This paper presents a divide and conquer solution to implement decentralize…

Quantum control is valuable for various quantum technologies such as high-fidelity gates for universal quantum computing, adaptive quantum-enhanced metrology, and ultra-cold atom manipulation. Although supervised machine learning and reinforcement learning are widely used for optimizing control parameters in classical …