A new algorithm for deep Q-learning with robustness to state transition uncertainty.
problem Model uncertainty in state transitions for non-tabular, continuous state spaces.
method Distributionally robust approach using worst-case transition ball and dualized Bellman operator with Sinkhorn distance.
result Optimal policy found through solving non-linear Bellman equation with neural network parameterization.
Study shows depth improves generalization in deep learning models.
problem Understanding why and when depth improves generalization in deep learning.
method Implementation-agnostic state-transition model to analyze depth and generalization.
result Identifies geometric and semigroup mechanisms that keep entropy contribution saturated or polynomial, clarifying depth's statistical advantage.
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…
A new method for ILO with transition model disparity using an intermediary policy.
problem Learning tasks from expert observations with different transition dynamics.
method Training an intermediary policy to match the state transitions of the expert dataset.
result Our method outperforms existing ILO approaches with transition model mismatch.
A Semi-Hidden Markov Model (SHMM) for bursty error channels is defined by a state transition probability matrix A, a prior probability vector Π, and the state dependent output symbol error probability matrix B. Several processes are utilized for estimating A, Π and B from a given empirically obtained or sim…
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…
New STH distance finds patterns in event timeseries without resampling.
problem Lack of efficient analysis methods for event and state timeseries.
method Define STE-ts, propose STH, leveraging both time and state duration.
result Improved precision and computation time compared to resampled metrics.
The paper proposes a survival model to optimize mobile notification delivery times.
problem Inappropriate notification timing and interruptions lead to user complaints.
method Developed a state transition framework and a survival model with log-linear and Weibull structures.
result The survival model outperforms logistic regression in prediction accuracy.
A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.
problem Estimating long-term care transition probabilities in irregular longitudinal health data.
method A neural network that learns from individual health history, incorporates time elapsed, and conditions on demographic and socioeconomic attributes.
result Improves severe disability discrimination and maintains strong calibration.
New issue found in value-based reinforcement learning for stochastic environments.
problem Value-based reinforcement learning struggles with stochastic state transitions.
method Demonstrated using a multiobjective Markov Decision Process (MOMDP).
result Approaches may converge to Pareto-dominated solutions instead of optimal ones.
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…
NESS improves neighbor embedding for smooth cell-state transitions in single-cell data.
problem Challenges in extracting smooth, low-dimensional representations from noisy single-cell data.
method Builds on PCS framework to develop NESS, a stable machine learning approach.
result NESS consistently yields useful biological insights across diverse single-cell datasets.
A new RL paradigm reduces state-action-value function approximation inefficiency.
problem Challenges in state-action-value function approximation for RL.
method State Action Separable Reinforcement Learning (sasRL) decouples action space from value function learning.
result sasRL achieves up to 75% better performance than state-of-the-art MDP-based RL algorithms.
Paper introduces a new value function for state transitions and optimal policy learning.
problem Learning optimal policies from state transitions and actions.
method Develops a forward dynamics model to maximize a novel value function Q(s,s′). result Demonstrates benefits in value function transfer, redundant action spaces, and off-policy learning.
This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DR…
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 method for state inference in state-space models with unknown dynamics.
problem State inference in state-space models with computationally expensive and undefined dynamics.
method Estimate state transition dynamics using a multi-output Gaussian process and Bayesian Neural Network as a surrogate model.
result Significant improvement in accuracy for state inference and prediction in non-stationary user models.
SA-GFN corrects biases in GFlowNets due to graph symmetries.
problem Systematic biases in state transition probability computations.
method Incorporates symmetry corrections into the learning process through reward scaling.
result Eliminates need for explicit state transition computations.
Deep active inference agents learn complex environments using Monte-Carlo methods.
problem Understanding and modeling biological intelligence in complex, continuous state-spaces.
method Neural architecture for deep active inference agents using multiple forms of Monte-Carlo sampling.
result Deep active inference agents can learn environmental dynamics and plan future actions.
Paper introduces OMD for ordered state transitions in SSMs.
problem Modeling ordered latent states in dynamic systems.
method Ordered Matrix Dirichlet (OMD) prior over ordered stochastic matrices.
result OMD models recover interpretable ordered latent structure without sacrificing predictive performance.
Defines Learning Analytics' foundational structure and scope.
problem Lack of theoretical foundation in Learning Analytics.
method Proposes an axiomatic theory based on psychological learning and LA methodology.
result Clarifies the epistemological stance of Learning Analytics and its limitations.
Study shows pre-event L2 liquidity state predicts crypto futures liquidity better than event labels.
problem Understanding how crypto futures liquidity changes over time.
method Combining L2 order book data, trade-flow records, and macro-event windows to define discrete liquidity-state transitions and evaluate models.
result Pre-event L2 liquidity state predicts post-event liquidity regimes better than event labels, and order flow adds value only when layered on top of the state model.
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding errors' when the model is unrolled step by step. Essentia…
Paper proposes a new framework for robust multi-modal data fusion under uncertainty.
problem Unexpected modality failures in nonlinear non-Gaussian dynamic processes.
method Dynamic model averaging (DMA) based particle filter (PF) algorithm.
result The proposed solution outperforms state-of-the-art methods in experiments.
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.
problem Robustness and safety in deep reinforcement learning with limited data assumptions.
method Optimal transport perturbations to construct worst-case virtual state transitions.
result Significantly improved safety at deployment time compared to standard methods.
Unified ML approach for SDEs in bounded domains.
problem Challenges in simulating SDEs with particle exit phenomena.
method Hybrid approach combining diffusion model and exit prediction network.
result Accurate modeling of interior dynamics and boundary interactions.
Neural Physicist learns physical dynamics from images.
problem Learning meaningful physical state representations and accurate state transitions from image sequences.
method Neural Physicist uses VAE for state extraction, NP for parameters, and SSM for dynamics.
result Achieves long-term predictions and identifies system degrees of freedom.
The paper develops a valuation framework for GLWB-LTC contracts with Levy dynamics and stochastic interest rates.
problem Valuation of GLWB-LTC contracts with financial guarantees, longevity protection, and health-contingent LTC payments.
method Coupling a recombining Hull-White trinomial tree with an IMEX finite difference scheme, incorporating a seven-state health model.
result Hybrid tree-IMEX method delivers stable long-maturity prices consistent with simulation benchmarks.
Study generalizes Picard iteration for nonlinear PDEs, deriving bounds on error.
problem Generalize Picard iteration for nonlinear parabolic PDEs.
method Formulate Picard iteration as abstract state-transition model, derive generalization error bounds.
result Picard depth reduction reduces Picard truncation error without increasing estimation error.
MaxMax Q-Learning improves coordination in multi-agent reinforcement learning by refining action selection.
problem Relative over-generalization in decentralized multi-agent reinforcement learning.
method MaxMax Q-Learning employs iterative sampling and evaluation of potential next states to refine approximations of ideal state transitions.
result MaxMax Q-Learning frequently outperforms existing baselines, demonstrating enhanced convergence and sample efficiency.
This paper proposes a stochastic model using the concept of Markov chains for the inter-state transitions of the millisecond order quasi-stable phase synchronized patterns or synchrostates, found in multi-channel Electroencephalogram (EEG) signals. First and second order transition probability matrices are estimated fo…
CEA augments reinforcement learning by generating counterfactual experiences.
problem Challenges in reinforcement learning, especially out-of-distribution and inefficient exploration.
method CEA uses variational autoencoders to model state transitions and introduces randomness for non-stationarity. It expands learning data through counterfactual inference.
result CEA outperforms SOTA algorithms in diverse environments.
Study identifies transitions between traffic modes on Cologne motorways.
problem Understanding transitions between different traffic modes.
method Constructed state transition network, identified dominant states using PageRank algorithm.
result Identified seasonal dependence in traffic modes.
In this work, sequence-to-sequence (seq2seq) models, originally developed for language translation, are used to predict the temporal evolution of complex, multi-physics computer simulations. The predictive performance of seq2seq models is compared to state transition models for datasets generated with multi-physics cod…
Kernel Bayesian inference is a principled approach to nonparametric inference in probabilistic graphical models, where probabilistic relationships between variables are learned from data in a nonparametric manner. Various algorithms of kernel Bayesian inference have been developed by combining kernelized basic probabil…
Study learns linear system dynamics from noisy bilinear data.
problem Learning linear dynamics from bilinear observations with process and measurement noise.
method Regression with Kronecker product design, data-dependent and independent error bounds.
result Upper bounds on statistical error rates and sample complexity for learning dynamics matrices.
Federated learning interprets temporal dynamics across clients with graph attention.
problem Interpreting temporal patterns across decentralized, heterogeneous systems with nonlinear dynamics.
method Graph Attention Network for learning state transition models over latent states communicated between clients.
result First interpretable characterization of cross-client temporal interdependencies in decentralized nonlinear systems.
Paper proposes a dual-level approach for multi-step forecasting of dynamical systems.
problem Accurate multi-step forecasting of time series systems for automatic control and optimization.
method Hybrid input forecasting using LSTM-STMs and physics-informed neural networks (PINNs).
result Hybrid models achieve higher log-likelihood and lower MSE compared to conventional methods.
A new method reduces high-dimensional state space for dynamic choice models.
problem Estimation of dynamic discrete choice models is computationally intensive and infeasible in high-dimensional settings.
method Recursive partitioning algorithm to reduce dimensionality of high-dimensional state space.
result Our method reduces estimation bias and makes estimation feasible.
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However, autoregressive feedback exposes the evolution of the hidden state trajectory to potential biases from well-known train-test discrepancies.…
Bottom-Up Hidden Tree Markov Model is a highly expressive model for tree-structured data. Unfortunately, it cannot be used in practice due to the intractable size of its state-transition matrix. We propose a new approximation which lies on the Tucker factorisation of tensors. The probabilistic interpretation of such ap…
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
The paper uses a novel framework to learn option prices by imitating principal investor behavior.
problem Challenges in modeling stock price changes and decision making in equity markets.
method Non-deterministic Markov decision process, Bayesian deep neural network, reinforcement learning.
result Optimal option prices learned through imitation of principal investor behavior.
We present a novel approach for learning an HMM whose outputs are distributed according to a parametric family. This is done by {\em decoupling} the learning task into two steps: first estimating the output parameters, and then estimating the hidden states transition probabilities. The first step is accomplished by fit…
We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an algorithm and provide performance guarantees for the regret evaluated against the…
GGP models multivariate time series with latent sub-sequences for diverse behaviors.
problem Modeling multivariate time series with diverse behaviors and patterns.
method Graph Gamma Process (GGP) linear dynamical systems with latent sub-sequences.
result GGP models exhibit good predictive performance and reveal interpretable latent patterns.
Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more general case the learner does not know a priori what the action space is. Here we …