arXiv research

Paper proposes a new Markov model for efficient PLC system design.

This work identifies eigenvalues of unknown linear dynamics without full system identification.

Paper introduces OMD for ordered state transitions in SSMs.

A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.

Solves steering problem with continuous time, Hilbert-Schmidt cost, and matrix ODEs.

A new algorithm for deep Q-learning with robustness to state transition uncertainty.

Study learns linear system dynamics from noisy bilinear data.

A novel probabilistic approach forecasts imbalance prices in Belgium.

Paper benchmarks DRL policies' resilience to state transitions.

Study shows depth improves generalization in deep learning models.

New algorithms achieve logarithmic regret in learning linear quadratic control systems.

A new method for ILO with transition model disparity using an intermediary policy.

We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and…

New STH distance finds patterns in event timeseries without resampling.

Model reduction of Markov processes is a basic problem in modeling state-transition systems. Motivated by the state aggregation approach rooted in control theory, we study the statistical state compression of a discrete-state Markov chain from empirical trajectories. Through the lens of spectral decomposition, we study…

Bayesian tensor factorization approximates a complex tree model.

We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state transition setting, namely the setting of deterministic policy gradient (DPG). We firstl…

A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is proposed to model sequentially observed multivariate data. SGLDS uses the Bernoulli-Poisson link together with a gamma process to generate an infinite dimensional sparse random graph to model state transitions. Depending on the sparsity pattern of…

A new method for state estimation in state-space models using incomplete data.

NESS improves neighbor embedding for smooth cell-state transitions in single-cell data.

The paper proposes a survival model to optimize mobile notification delivery times.

New issue found in value-based reinforcement learning for stochastic environments.

Watermarks DRL policies with minimal performance impact.

SA-GFN corrects biases in GFlowNets due to graph symmetries.

Defines Learning Analytics' foundational structure and scope.

GGP models multivariate time series with latent sub-sequences for diverse behaviors.

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference \emph{and learning} (i.e. state estimation and system identification) in nonlinear nonparametric state-space models. We place a Gauss…

Paper introduces a new value function for state transitions and optimal policy learning.

A new RL paradigm reduces state-action-value function approximation inefficiency.

The transition amplitudes between coherent states on a coherent state manifold are expressed in terms of the embedding of the coherent state manifold into a projective Hilbert space. Consequences for the dimension of projective Hilbert space and a simple geometric interpretation of Calabi's diastasis follows.

Safe reinforcement learning framework using optimal transport for robustness.

New insights into spectral statistics of sample covariance matrix for stable linear systems.

Deep active inference agents learn complex environments using Monte-Carlo methods.

MaxMax Q-Learning improves coordination in multi-agent reinforcement learning by refining action selection.

Study identifies transitions between traffic modes on Cologne motorways.

Mamba struggles with long context lengths, but spectrum scaling improves performance.

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both…

New algorithm minimizes regret in sparse reinforcement learning.

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

State2vec improves RL by learning state embeddings that generalize across policies.

Unified framework for solving MDPs with stochastic mirror descent.

New method learns high-quality Laplacian representations for reinforcement learning.

Study shows pre-event L2 liquidity state predicts crypto futures liquidity better than event labels.

The paper develops a valuation framework for GLWB-LTC contracts with Levy dynamics and stochastic interest rates.

Paper proposes a new framework for robust multi-modal data fusion under uncertainty.

Neural Physicist learns physical dynamics from images.

Unified ML approach for SDEs in bounded domains.

CEA augments reinforcement learning by generating counterfactual experiences.