arXiv research

New method models unknown systems with hidden parameters using neural networks.

Efficient algorithm for unknown linear systems with convex costs.

FML uses neural networks to model unknown systems accurately.

Bayesian method synthesizes barrier certificates for unknown systems with latent states.

New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.

MAGI-X learns unknown dynamics from data without numerical integration.

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…

Method learns model for unknown stochastic system from data.

Advanced and effective collaborative filtering methods based on explicit feedback assume that unknown ratings do not follow the same model as the observed ones (\emph{not missing at random}). In this work, we build on this assumption, and introduce a novel dynamic matrix factorization framework that allows to set an ex…

Despite significant effort in understanding complex systems (CS), we lack a theory for modeling, inference, analysis and efficient control of time-varying complex networks (TVCNs) in uncertain environments. From brain activity dynamics to microbiome, and even chromatin interactions within the genome architecture, many …

Method learns dynamics of slow variables from stochastic data.

Bayesian algorithm stabilizes unknown continuous-time systems from unstable data.

Study optimal control in unknown nonlinear systems with near-optimal regret bound.

New RL approach learns dynamic VCG mechanisms in unknown MDP environments.

Deep learning predicts dynamics from sparse data.

Greedy policy maximizes information in unknown linear systems.

Estimates system parameters from a single observation using kernel-based score.

New method for state inference in state-space models with unknown dynamics.

Improved RL algorithm stabilizes unknown linear systems with polynomial regret.

KCRL learns stable policies for nonlinear systems with formal guarantees.

Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. Especially when the latter is not available, multi-kernel learning has gained popularity thanks to its flexibility in ch…

New algorithm controls systems with unknown, changing losses.

Framework LiLY recovers latent causal variables from time-series data under distribution shifts.

Optimal pricing strategy for unknown valuation models with noisy feedback.

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

Guaranteed reachable set for unknown nonlinear systems on manifolds.

Develops $Φ$-DVAE for assimilating unstructured data into physical models.

Bayesian framework integrates prior and data knowledge for nonlinear dynamical systems.

Bayesian ODEs with Gaussian processes infer unknown dynamics from data.

Develops inverse EKF for non-linear systems with stability guarantees and learning unknown dynamics.

In conventional ODE modelling coefficients of an equation driving the system state forward in time are estimated. However, for many complex systems it is practically impossible to determine the equations or interactions governing the underlying dynamics. In these settings, parametric ODE model cannot be formulated. Her…

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…

In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli which caused them. The Bayesian solution to this problem is known as a Bayes filter, which applies Bayes' rule to combine population responses with the pr…

A new growth model for dynamic networks using Markovian latent points.

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.

New algorithm adapts to unknown demand smoothness for dynamic pricing.

We present a general numerical approach for learning unknown dynamical systems using deep neural networks (DNNs). Our method is built upon recent studies that identified the residue network (ResNet) as an effective neural network structure. In this paper, we present a generalized ResNet framework and broadly define res…

Study learns linear system dynamics from noisy bilinear data.

CoCoRL learns safe constraints from demonstrations with unknown rewards.

Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simp…

Study on identifying and inferring nonlinear dynamics on unknown networks.

This paper considers portfolio construction in a dynamic setting. We specify a loss function comprised of utility and complexity components with an unknown tradeoff parameter. We develop a novel regret-based criterion for selecting the tradeoff parameter to construct optimal sparse portfolios over time.

Efficiently learns MFC systems with unknown dynamics.

The optimal predictor for a linear dynamical system (with hidden state and Gaussian noise) takes the form of an autoregressive linear filter, namely the Kalman filter. However, a fundamental problem in reinforcement learning and control theory is to make optimal predictions in an unknown dynamical system. To this end, …

Generative ODE model learns unknown variables in medical systems.

In the present paper, we studied a Dynamic Stochastic Block Model (DSBM) under the assumptions that the connection probabilities, as functions of time, are smooth and that at most $s$ nodes can switch their class memberships between two consecutive time points. We estimate the edge probability tensor by a kernel-type p…

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the …