arXiv research

Paper tackles online optimization with memory and competitive control.

Challenge encourages reproducible deep learning methods.

Develops a learning model predictive controller for competitive racing.

We consider Online Convex Optimization (OCO) in the setting where the costs are $m$-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive rat…

Combining causality, control, and reinforcement learning for system control.

Study strategic competition in commodity markets using impulse-switching controls.

RL controls small soccer robots in a real league, beating human-designed policies.

A drone catches another agile drone using competitive reinforcement learning.

Investigates portfolio selection among competitive agents with mean-variance preferences.

Study competitive energy markets using stochastic impulse games.

The control of the costs, as soon as possible of the product life cycle, became a major asset in the competitiveness of the companies confronted with the universalization of competition. After having proposed the problems related this control difficulties, we will present an approach defining a concept of cost entity r…

In the early phases of the product life cycle, the costs controls became a major decision tool in the competitiveness of the companies due to the world competition. After defining the problems related to this control difficulties, we will present an approach using a concept of cost entity related to the design and real…

Study explores optimal strategies in games with multiple players and mean-field interactions.

Adapts model-based advice to stabilize black-box policies for nonlinear control.

Investors' strategic trading affects asset prices, modeled as a game.

We consider a class of discrete time stochastic control problems motivated by some financial applications. We use a pathwise stochastic control approach to provide a dual formulation of the problem. This enables us to develop a numerical technique for obtaining an estimate of the value function which improves on purely…

The structure of the control network of transnational corporations affects global market competition and financial stability. So far, only small national samples were studied and there was no appropriate methodology to assess control globally. We present the first investigation of the architecture of the international …

Study aims to develop a humanoid robot dialogue system.

Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving the urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal contr…

Modeling dealer competition, internalisation and externalisation impact market dynamics and costs.

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

Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Co…

SHADOWCAST generates graphs with user-specified attributes.

Distributed, controllable energy storage devices offer several benefits to electric power system operation. Three such benefits include reducing peak load, providing standby power, and enhancing power quality. These benefits, however, are only realized during peak load or during an outage, events that are infrequent. T…

In this paper, we present a novel penalty approach for the numerical solution of continuously controlled HJB equations and HJB obstacle problems. Our results include estimates of the penalisation error for a class of penalty terms, and we show that variations of Newton's method can be used to obtain globally convergent…

Pakistan examines digital mergers using traditional competition tools.

Multivariate boosted trees improve forecasting and control by capturing correlated predictions.

We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games. In this class, players control the inputs of a smooth function whose output is being applied to a bilinear zero-sum game. This class of games is motivated by the indirect nature of the competition in Ge…

Machine learning boosts RCT efficiency by controlling type I error and improving statistical power.

Competition aims to develop sample-efficient reinforcement learning methods.

Decentralized detection avoids sharing data, controls false discoveries.

Simple online monitor detects unsafe LLM outputs.

NeurT-FDR controls FDR by incorporating feature hierarchy.

Geometric theory explains substitutability in market outcomes based on production constraints.

Paper tackles AI driving competition challenges with mixed simulation and real-world data.

FDN improves probabilistic regressors' adaptability to distribution shifts.

We study the dynamics of co-evolution of producers and customers described by bit-strings representing individual traits. Individual ''size-like'' properties are controlled by binary encounters which outcome depends upon a recognition process. Depending upon the parameter set-up, mutual selection of producers and custo…

A communication-efficient method controls FDR in network settings.

To overcome the oscillation problem in the classical momentum-based optimizer, recent work associates it with the proportional-integral (PI) controller, and artificially adds D term producing a PID controller. It suppresses oscillation with the sacrifice of introducing extra hyper-parameter. In this paper, we start by …

Modeling pollution from competing firms using mean-field games.

The Interactive Minority Game (IMG) is an online version of the traditional Minority Game in which human players can enter into competition with the traditional computer-controlled agents. Through the rich (and, importantly, analytically understood) behaviour of the MG, we can explore humans' behaviour in different kin…

The paper develops algorithms for competitive RL in partially observable MGs.

NeurT-FDR controls FDR by incorporating auxiliary covariates in deep learning.

Generative Adversarial Networks (GANs), though powerful, is hard to train. Several recent works (brock2016neural,miyato2018spectral) suggest that controlling the spectra of weight matrices in the discriminator can significantly improve the training of GANs. Motivated by their discovery, we propose a new framework for t…

Paper improves variance control in importance weighted variational bounds.

In this work we introduce two novel deterministic annealing based clustering algorithms to address the problem of Edge Controller Placement (ECP) in wireless edge networks. These networks lie at the core of the fifth generation (5G) wireless systems and beyond. These algorithms, ECP-LL and ECP-LB, address the dominant …

Optimistic RL algorithms are simplified for deep RL with competitive performance.

Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables. Amortized gradient-based learning of SCFMs is challenging as most approaches targeting discrete variables rely on their continuous relaxations---which can be intractable in SCFMs, as…