On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Partially Observable”

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learningcs.LG

New algorithm improves reinforcement learning from partial observations.

problem Inferior performance of algorithms in real-world reinforcement learning due to partial observability.

method Representation-based approach to POMDPs, leading to a tractable algorithm.

result Empirically demonstrates superior performance with partial observations.

reinforcement learning partial observability POMDPs algorithmic approach statistical efficiency

2023-11-20abs ↗pdf ↗

Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observationcs.LG

Efficient RL in partially observable risk-sensitive environments with hindsight observations.

problem Risk-sensitive reinforcement learning in partially observable environments.

method Integrates hindsight observations into POMDP framework, develops novel RL algorithm.

result Achieves polynomial regret with provable efficiency, outperforming existing methods.

reinforcement learning risk-sensitive partially observable hindsight observation partial observability

2024-02-28abs ↗pdf ↗

The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processesmath.OC

We characterize value functions in partially observable MDPs as semi-algebraic sets.

problem Understanding feasible value functions in partially observable Markov decision processes.

method Characterization of feasible value functions as semi-algebraic sets defined by polynomial inequalities.

result The feasible set of value functions in POMDPs is a semi-algebraic set, not a polytope as in MDPs.

value function Markov decision process partially observable semi-algebraic set policy optimization

2026-06-02abs ↗pdf ↗

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systemscs.LG

New framework learns policies for partially observable systems.

problem Learning policies in partially observable dynamical systems.

method Partially Observable Bilinear Actor-Critic framework.

result Algorithm can learn against optimal policies in certain cases.

Reinforcement Learning Partial Observability Function Approximation Actor-Critic POMDPs

2022-06-24abs ↗pdf ↗

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycs.LG

RL struggles with generalization due to implicit partial observability.

problem Generalization in RL is difficult due to implicit partial observability.

method Re-cast RL problem as solving epistemic POMDPs and propose ensemble-based techniques.

result Simple ensemble-based technique achieves significant generalization gains.

Reinforcement Learning Generalization Epistemic POMDP Partial Observability Procgen

2021-07-13abs ↗pdf ↗

Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBMstat.ML

PCBM improves neural network generalization by partially observing concepts.

problem Decreased generalization performance due to observing all concepts in CBM.

method Developed a theoretical analysis of PCBM's Bayesian generalization error.

result PCBM's generalization error is lower than CBM's due to partial concept observation.

Bayesian generalization Concept bottleneck model Neural networks Partial observation Generalization performance

2024-03-14abs ↗pdf ↗

Causally Correct Partial Models for Reinforcement Learningcs.LG

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the observations are high-dimensional (e.g. images). For this reason, previous works have…

2020-02-07abs ↗pdf ↗

Minimax-Optimal Policy Regret in Partially Observable Markov Gamescs.LG

Study optimal policy regret in partially observable Markov games with adaptive opponents.

problem Optimal sequential decision-making in partially observable environments against strategic, adaptive opponents.

method An epoch-based optimistic maximum-likelihood algorithm that selects one policy per epoch using confidence sets built cumulatively from past data.

result Achieves

ilde{O}(\sqrt{T})

policy regret for fixed problem parameters, with explicit dependence on horizon, adversary memory, confidence radius, and aggregate Eluder dimension.

Markov Games Sequential Decision Making Adversarial Learning Optimistic Algorithms Partial Observability

2026-06-01abs ↗pdf ↗

Posterior Sampling for Competitive RL: Function Approximation and Partial Observationcs.LG

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

problem Challenges in reinforcement learning with function approximation and partial observability.

method Proposes posterior sampling methods for self-play and adversarial learning in zero-sum MGs.

result Developed algorithms achieve low regret bounds scaling sublinearly with GEC and episode number.

reinforcement learning competitive games posterior sampling function approximation partial observability

2023-10-30abs ↗pdf ↗

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedbackcs.LG

RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.

problem Failure of reinforcement learning from human feedback in partially observable environments.

method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.

result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.

reinforcement learning human feedback partial observability deception overjustification

2024-02-27abs ↗pdf ↗

Online Bayesian Experimental Design for Partially Observed Dynamical Systemsstat.ML

New BED method handles online inference for partially observed dynamical systems.

problem Optimizing data collection for partially observable, partially online dynamical systems.

method Derived estimators of expected information gain and its gradient for SSMs, using nested particle filters.

result Successfully handles both partial observability and online inference in realistic models.

Bayesian experimental design state-space models online inference partial observability particle filters

2025-11-06abs ↗pdf ↗

When Is Partially Observable Reinforcement Learning Not Scary?cs.LG

New algorithm proves RL from partial obs is feasible.

problem Difficulty in learning from partial observability.

method Optimism combined with MLE for weakly revealing POMDPs.

result Simple algorithm guarantees polynomial sample efficiency.

Reinforcement Learning Partial Observability POMDPs Optimism Maximum Likelihood Estimation

2022-04-19abs ↗pdf ↗

Learning Causal States Under Partial Observability and Perturbationcs.LG

Enhances RL in partially observable, noisy environments by uncovering causal states.

problem Making decisions based on incomplete and noisy observations in partially observable Markov decision processes (P

^2

OMDPs).

method Causal State Representation under Asynchronous Diffusion Model (CaDiff) framework, incorporating a novel asynchronous diffusion model (ADM) and a new bisimulation metric.

result Enhances returns by at least 14.18% compared to baselines on Roboschool tasks.

Reinforcement Learning Partial Observability Perturbation Causal States Diffusion Models

2025-11-29abs ↗pdf ↗

Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithmscs.LG

This paper advances sample-efficient learning for partially observable RL by introducing B-stability and new algorithms.

problem Hard sample complexity for learning near-optimal policies in partially observable RL.

method Proposes B-stability as a unified structural condition and develops new algorithms for sample-efficient learning.

result Any B-stable PSR can be learned with polynomial samples, improving over current best complexities.

Reinforcement Learning Partial Observability B-stability Sample-Efficient Predictive State Representations

2022-09-29abs ↗pdf ↗

Risk-Sensitive Mean-Field Type Control under Partial Observationmath.OC

We establish a stochastic maximum principle (SMP) for control problems of partially observed diffusions of mean-field type with risk-sensitive performance functionals.

2014-11-26abs ↗pdf ↗

Structural Estimation of Partially Observable Markov Decision Processescs.LG

The paper develops methods to estimate POMDPs from partial information.

problem Making decisions under partial information about state variables.

method Structural estimation of POMDP primitives using observable history.

result Conditions for model identifiability without state dynamics knowledge.

POMDP structural estimation partial observability maximum likelihood policy gradient

2020-08-02abs ↗pdf ↗

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Priorcs.LG

New algorithm infers trajectories from partial observations using optimal transport.

problem Inferring trajectories from partial observations of coupled systems.

method Extends MFL algorithm to latent SDEs using observable state space models and partial observations.

result Experiments show significant outperformance over latent-free baseline.

optimal transport latent SDEs observable state space models partial observations trajectory inference

2024-06-11abs ↗pdf ↗

A Sparsity Principle for Partially Observable Causal Representation Learningcs.LG

New method identifies causal variables from partially observed data.

problem Learning from unpaired observations with instance-dependent partial observability.

method Proposes two methods enforcing sparsity in the inferred representation.

result Establishes two identifiability results for linear and piecewise linear mixing functions.

causal representation learning partial observability sparsity principle identifiability mixed functions

2024-03-13abs ↗pdf ↗

Decentralized policy learning with partial observation and mechanical constraints for multiperson modelingcs.LG

We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.

problem Modeling real-world multi-agent behaviors with limited observation and mechanical constraints.

method Decentralized generative models with partial observation and mechanical constraints based on hierarchical variational recurrent neural networks.

result Our method effectively models and predicts biologically plausible behaviors with minimal constraint violations.

multi-agent modeling partial observation mechanical constraints behavioral analysis biological plausibility

2020-07-07abs ↗pdf ↗

Off-Policy Evaluation in Partially Observable Environmentscs.LG

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…

2019-09-09abs ↗pdf ↗

Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiencycs.LG

Study efficient reinforcement learning for partially observed systems with linear structure.

problem Efficient reinforcement learning for partially observed Markov decision processes with linear structure.

method Proposes OP-TENET algorithm using a Bellman operator with finite memory, adversarial integral equation, and optimistic exploration.

result Achieves ε-optimal policy within O(1/ε^2) episodes with polynomial sample complexity in intrinsic dimension.

Reinforcement Learning Partial Observability Linear Function Approximation Sample Efficiency POMDPs

2022-04-20abs ↗pdf ↗

Policy Gradient in Partially Observable Environments: Approximation and Convergencecs.LG

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully observable environments. In this paper, we generalize a variety of these advances to part…

2018-10-18abs ↗pdf ↗

Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Banditsstat.ML

New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.

problem Improving Thompson Sampling for partially observed context bandits.

method Proposed a Thompson Sampling algorithm for partially observable contextual multi-armed bandits with theoretical performance guarantees.

result Regret scales logarithmically with time and the number of arms, and linearly with the dimension.

Thompson Sampling Contextual Bandits Partial Observability Regret Analysis

2021-10-23abs ↗pdf ↗

Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systemscs.LG

Proposes neural delay differential equations for stable system identification with partially observed states.

problem Learning stable models for systems with partial or delayed observations.

method Augments states with history, uses neural delay differential equations, and ensures stability through time delay analysis.

result The approach ensures stability of learned models for partially observed systems.

neural networks differential equations system identification stability delayed systems

2021-10-27abs ↗pdf ↗

Efficient Spectral Control of Partially Observed Linear Dynamical Systemscs.LG

New method controls linear systems with partial info and disturbances.

problem Controlling linear dynamical systems under partial observation and adversarial disturbances.

method Double Spectral Control (DSC) using two-level spectral approximation strategy.

result Matches best known regret guarantees with exponential runtime improvement.

linear dynamical systems partial observation spectral control adversarial disturbances

2025-05-27abs ↗pdf ↗

Constrained Bayesian Optimization Under Partial Observations: Balanced Improvements and Provable Convergencecs.LG

Efficient method for constrained optimization under partial observations with provable convergence.

problem Optimizing under partial and constrained data.

method Improved acquisition functions and Gaussian process embedding for partially observable constraints.

result Empirically validated method outperforms traditional approaches.

Bayesian optimization Constrained optimization Partial observations Gaussian process Convergence

2023-12-06abs ↗pdf ↗

Mean field equilibrium asset pricing model under partial observation: An exponential quadratic Gaussian approachq-fin.PR

The paper models asset pricing in a partially observed market using mean field game theory and exponential quadratic Gaussian framework.

problem Asset pricing in a market with partial observation and heterogeneous agents.

method Mean field game theory, exponential quadratic Gaussian framework, Kalman-Bucy filtering theory.

result Characterization of equilibrium risk premium through mean field BSDE and construction of unobservable risk premium process.

asset pricing mean field game partial observation exponential quadratic Gaussian Kalman-Bucy filtering

2024-10-02abs ↗pdf ↗

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observationstat.ML

New model captures state-dependent variability in partially observed systems.

problem Structured stochasticity not captured by constant-variance models.

method State-coupled stochastic volatility framework with particle expectation-maximization.

result Model consistently reduces recovery bias under partial observation.

state-space models stochastic volatility latent dynamics partial observation particle filtering

2026-06-01abs ↗pdf ↗

Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processescs.LG

PRL improves off-policy evaluation in partially observed MDPs.

problem Confounding and bias in offline reinforcement learning with unobserved state factors.

method Extends proximal causal inference to POMDPs, identifying and estimating target policy value.

result Semiparametrically efficient estimators for PRL in partially observed MDPs.

Reinforcement Learning Partial Observability Proximal Causal Inference Sepsis Management Off-Policy Evaluation

2021-10-28abs ↗pdf ↗

Partially Observable Contextual Bandits with Linear Payoffscs.LG

New algorithm for partially observable contexts in finance.

problem Decision making based on partially observable, correlated market information.

method EMKF-Bandit algorithm integrating system identification, filtering, and bandit algorithms.

result Sub-linear regret under conditions on filtering.

contextual bandits financial decision making partial observability linear payoffs statistical signal processing

2024-09-17abs ↗pdf ↗

Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancycs.LG

A new metric detects non-Markovian states in partially observable environments.

problem Learning state representations in partially observable environments.

method Introducing the

λ

-discrepancy metric to detect non-Markovian states.

result The

λ

-discrepancy is zero for Markov processes and non-zero for partially observable environments.

Reinforcement Learning Partial Observability Temporal Difference Markov Decision Processes Memory Function

2024-07-10abs ↗pdf ↗

On Improving Deep Reinforcement Learning for POMDPscs.LG

Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architec…

2018-04-17abs ↗pdf ↗

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscs.LG

Paper proposes learning system dynamics from irregularly-sampled partial observations.

problem Capturing dynamics of multi-agent systems with irregular and partial observations.

method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.

result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.

system dynamics partial observations multi-agent systems graph neural networks neuralODE

2020-11-08abs ↗pdf ↗

Ensemble score filter with image inpainting for data assimilation in tracking surface quasi-geostrophic dynamics with partial observationsphysics.ao-ph

EnSF uses image inpainting to handle partial observations in data assimilation.

problem Data assimilation challenges with partial observations.

method EnSF integrates image inpainting with diffusion models to predict unobserved states.

result EnSF successfully tracks SQG dynamics with partial observations.

data assimilation image inpainting machine learning partial observations surface quasi-geostrophic dynamics

2025-01-20abs ↗pdf ↗

Linear Bandits with Partially Observable Featuresstat.ML

We tackle linear bandits with partially observable features, achieving sublinear regret.

problem Linear regret due to unobserved features in partially observable linear bandits.

method Feature augmentation with orthogonal basis vectors and a doubly robust estimator.

result Sublinear regret bound of

ilde{O}(\sqrt{(d + d_h)T})

linear bandits partially observable features regret minimization feature augmentation doubly robust estimator

2025-02-10abs ↗pdf ↗

Sample-Efficient Reinforcement Learning of Partially Observable Markov Gamescs.LG

This paper tackles sample-efficient reinforcement learning for partially observable Markov games.

problem Learning in partially observable Markov games with incomplete information.

method A simple algorithm combining optimism and Maximum Likelihood Estimation (MLE) for self-play, and a variant of optimistic MLE for adversarial opponents.

result The proposed algorithms achieve approximate Nash, correlated, and coarse correlated equilibria in polynomial samples for weakly revealing POMGs.

Reinforcement Learning Markov Games Partial Observability Optimism Maximum Likelihood Estimation

2022-06-02abs ↗pdf ↗

Thompson Sampling in Partially Observable Contextual Banditsstat.ML

Thompson Sampling improves decision-making in partially observed contexts.

problem Balancing exploration and exploitation in partially observed contextual bandits.

method Thompson Sampling policy for learning optimal arms from noisy linear functions of unobserved context vectors.

result Thompson Sampling achieves poly-logarithmic regret and square-root consistency of parameter estimation.

Thompson Sampling Contextual Bandits Exploration vs. Exploitation Partial Observations Regret Analysis

2024-02-15abs ↗pdf ↗

A PAC RL Algorithm for Episodic POMDPscs.LG

Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially …

2016-05-25abs ↗pdf ↗

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costscs.LG

New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.

problem Tackles inverse optimal control for non-linear partially observable systems.

method Probabilistic approach using maximum causal entropy formulations and local linearization.

result Disentangles perceptual factors and behavioral costs in sequential decision-making.

inverse optimal control non-linear systems partially observable perceptual uncertainty behavioral costs

2023-03-29abs ↗pdf ↗

Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learningstat.ML

Physics-constrained deep learning predicts geophysical dynamics with boundedness.

problem Forecasting geophysical systems with hidden variables and incomplete observations.

method Physics-constrained neural ordinary differential equation (NODE) representations with boundedness constraints.

result The approach generalizes learned dynamics to arbitrary initial conditions.

geophysical dynamics partial observations physics-constrained learning deep learning bounded dynamics

2022-02-11abs ↗pdf ↗

Adversarial Imitation Learning from Visual Observations using Latent Informationcs.LG

Algorithm improves imitation learning from visual data in partially observable environments.

problem Imitation learning from visual observations with missing expert actions and partial observability.

method Theoretical analysis and Latent Adversarial Imitation from Observations algorithm combining adversarial and latent representations.

result Latent Adversarial Imitation from Observations achieves state-of-the-art performance in high-dimensional robotic tasks.

imitation learning adversarial methods latent representations reinforcement learning partial observability

2023-09-29abs ↗pdf ↗

COMPILED: Deep Metric Learning for Defect Classification of Threaded Pipe Connections using Multichannel Partially Observed Functional Datacs.LG

A new deep metric learning method for defect classification in threaded pipe connections.

problem Defect classification in threaded pipe connections with limited and imbalanced multichannel functional data.

method COMPILED approach based on deep metric learning for imbalanced, multichannel, and partially observed functional data.

result Superior accuracy compared to existing benchmarks in a real-world case study.

defect classification threaded pipe connections multichannel functional data deep metric learning imbalanced data

2024-04-04abs ↗pdf ↗

Joint Registration and Conformal Prediction for Partially Observed Functional Datastat.ME

Unified approach for predicting missing segments in partially observed functions.

problem Predicting missing segments in partially observed functions with complex dependence and irregular noise.

method Unified registration and prediction approach under the conformal prediction framework, integrating amplitude and phase components.

result Effective prediction bands with finite-sample marginal coverage guarantees under weak assumptions.

functional data conformal prediction registration missing data phase variation

2025-02-20abs ↗pdf ↗

Optimistic MLE -- A Generic Model-based Algorithm for Partially Observable Sequential Decision Makingcs.LG

OMLE combines optimism and MLE for efficient sequential decision making.

problem Efficiently solving sequential decision making problems, especially in partially observable settings.

method Combines optimism for exploration and maximum likelihood estimation for model learning.

result OMLE learns near-optimal policies for a wide range of sequential decision making problems.

Sequential Decision Making Model-based Reinforcement Learning Optimism for Exploration Maximum Likelihood Estimation Partially Observable

2022-09-29abs ↗pdf ↗

Partially-Observable Sequential Change-Point Detection for Autocorrelated Data via Upper Confidence Regionstat.ML

AUCRSS detects change points in partially observed multivariate autocorrelated data.

problem Detecting change points in multivariate autocorrelated data with limited sensing resources.

method Adaptive Upper Confidence Region (AUCRSS) with state space model (SSM), adaptive sampling policy, and generalized likelihood ratio test.

result The method outperforms existing approaches in detecting change points efficiently.

change point detection autocorrelated data partial observability state space model upper confidence region

2024-03-30abs ↗pdf ↗

Stochastic Linear Bandits with Partially Observed Actionscs.LG

TOFU-POV tackles partially observed linear bandits, achieving sublinear regret with low-dimensional action vectors.

problem Stochastic linear bandits with partially observed actions in settings like recommendation and healthcare.

method TOFU-POV estimates latent action subspace, imputes missing actions, and runs OFUL in low-dimensional coordinates.

result TOFU-POV achieves

\sqrt{T}

regret scaling with intrinsic subspace dimension, improving upon natural baselines.

stochastic linear bandits partial observability low intrinsic dimension sublinear regret recommendation systems

2026-07-09abs ↗pdf ↗

Matrix Completion from Non-Uniformly Sampled Entriescs.LG

In this paper, we consider matrix completion from non-uniformly sampled entries including fully observed and partially observed columns. Specifically, we assume that a small number of columns are randomly selected and fully observed, and each remaining column is partially observed with uniform sampling. To recover the …

2018-06-27abs ↗pdf ↗

Regret Minimization in Partially Observable Linear Quadratic Controlcs.LG

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov parameters and then follows the principle of optimism in the face of uncertainty to desig…

2020-01-31abs ↗pdf ↗