arXiv research

Complexity measures for neural nets with general activations using path-based norms.

New method constructs Birkhoff sections for pseudo-Anosov flows with controlled complexity.

This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.

The control of complex systems is of critical importance in many branches of science, engineering, and industry. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automo…

Study nonparametric estimator for Markov chain transition matrices in offline setting.

New measure shows various training techniques control model complexity.

Novel method controls complex physical systems over long time frames.

Modern control theories such as systems engineering approaches try to solve nonlinear system problems by revelation of causal relationship or co-relationship among the components; most of those approaches focus on control of sophisticatedly modeled white-boxed systems. We suggest an application of actor-critic reinforc…

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…

Learning to control linear systems is statistically hard, especially for underactuated systems.

New findings on depth vs. width in neural networks, showing depth can improve learnability.

Random features enhance control of complex systems.

Study controls bifurcations in Eulerian flows with multiple Hopf singularities.

Majorizing measures control sequential complexities for online learning.

This work discusses a closed-loop control strategy for complex systems utilizing scarce and streaming data. A discrete embedding space is first built using hash functions applied to the sensor measurements from which a Markov process model is derived, approximating the complex system's dynamics. A control strategy is t…

The paper explores when linear system identification is hard or easy, especially for under-actuated systems.

HiDe learns hierarchical control for complex tasks by separating planning and control.

Paper proposes a DRL-based controller for networked AP systems that reduces communication frequency.

We discuss controlled connectivity properties of closed 1-forms and their cohomology classes and relate them to the simple homotopy type of the Novikov complex. The degree of controlled connectivity of a closed 1-form depends only on positive multiples of its cohomology class and is related to the Bieri-Neumann-Strebel…

Polynomial-time reachability for LTI systems with TLL NN controllers is achieved.

Networks of coupled dynamical systems provide a powerful way to model systems with enormously complex dynamics, such as the human brain. Control of synchronization in such networked systems has far reaching applications in many domains, including engineering and medicine. In this paper, we formulate the synchronization…

Deep learning solves complex stochastic control with jumps.

Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…

Breaks down complex nonlinear dynamics into simpler components.

Modern automation systems rely on closed loop control, wherein a controller interacts with a controlled process, based on observations. These systems are increasingly complex, yet most controllers are linear Proportional-Integral-Derivative (PID) controllers. PID controllers perform well on linear and near-linear syste…

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

A new method solves complex control problems with random coefficients.

This work develops a novel power control framework for energy-efficient power control in wireless networks. The proposed method is a new branch-and-bound procedure based on problem-specific bounds for energy-efficiency maximization that allow for faster convergence. This enables to find the global solution for all of t…

LineFlow is a framework for training RL agents to control production lines.

Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved…

CARL controls a quadruped to move naturally in complex environments.

Curriculum learning and imitation learning improve control over financial time-series data.

The paper addresses instability in KL divergence estimation using a neural network discriminator.

Collective behavior of the complex socio-economic systems is heavily influenced by the herding, group, behavior of individuals. The importance of the herding behavior may enable the control of the collective behavior of the individuals. In this contribution we consider a simple agent-based herding model modified to inc…

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constr…

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard …

Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image. Our approach is to use a learned perception map that predi…

A language for specifying complex reinforcement learning tasks.

PRISM infers model structures and parameters from simulations, controlling complexity at test time.

The paper proposes a method to identify causal structure in complex dynamical systems.

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

New method controls linear systems with partial info and disturbances.

Cross-regularization adapts model complexity during training.

Deep learning improves vehicle control performance and generalizes well.

This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of reinforcement learning and reviews competing solution paradigms. In order to compa…

Stochastic control problems in finance often involve complex controls at discrete times. As a result numerically solving such problems, for example using methods based on partial differential or integro-differential equations, inevitably give rise to low order accuracy, usually at most second order. In many cases one c…

Paper proposes method for optimal control of unknown systems with latent states.

In this paper a novel modification of the multilevel Monte Carlo approach, allowing for further significant complexity reduction, is proposed. The idea of the modification is to use the method of control variates to reduce variance at level zero. We show that, under a proper choice of control variates, one can reduce t…