Image de couverture de livre

Accelerated Online Risk-Averse Policy Evaluation in POMDPs with Theoretical Guarantees and Novel CVaR Bounds

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pariente, Yaacov, Indelman, Vadim
Format:	Preprint
Publié:	2026
Sujets:	Statistics Theory Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function
par: Pariente, Yaacov, et autres
Publié: (2026)

Simplification of Risk Averse POMDPs with Performance Guarantees
par: Pariente, Yaacov, et autres
Publié: (2024)

Bounding Conditional Value-at-Risk via Auxiliary Distributions with Bounded Discrepancies
par: Pariente, Yaacov, et autres
Publié: (2025)

POMDPPlanners: Open-Source Package for POMDP Planning
par: Pariente, Yaacov, et autres
Publié: (2026)

Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication
par: Shimron, Moshe Rafaeli, et autres
Publié: (2025)

Online POMDP Planning with Anytime Deterministic Optimality Guarantees
par: Barenboim, Moran, et autres
Publié: (2023)

Return Capping: Sample-Efficient CVaR Policy Gradient Optimisation
par: Mead, Harry, et autres
Publié: (2025)

A Martingale approach to continuous Portfolio Optimization under CVaR like constraints
par: Lelong, Jérôme, et autres
Publié: (2025)

Measurement Simplification in ρ-POMDP with Performance Guarantees
par: Yotam, Tom, et autres
Publié: (2023)

No Compromise in Solution Quality: Speeding Up Belief-dependent Continuous POMDPs via Adaptive Multilevel Simplification
par: Zhitnikov, Andrey, et autres
Publié: (2023)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
par: Wang, Kevin, et autres
Publié: (2026)

Conditional Performance Guarantee for Large Reasoning Models
par: Huang, Jianguo, et autres
Publié: (2026)

A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees
par: Yan, Hedong
Publié: (2025)

Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning
par: Zhitnikov, Andrey, et autres
Publié: (2024)

A Measure-Theoretic Axiomatisation of Causality
par: Park, Junhyung, et autres
Publié: (2023)

On the Provable Performance Guarantee of Efficient Reasoning Models
par: Zeng, Hao, et autres
Publié: (2025)

Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice
par: Lev-Yehudi, Idan, et autres
Publié: (2023)

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
par: Muni, Aneri, et autres
Publié: (2026)

Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes
par: Dong, Stella C.
Publié: (2025)

The Geometry of Knowing: From Possibilistic Ignorance to Probabilistic Certainty -- A Measure-Theoretic Framework for Epistemic Convergence
par: Jah, Moriba Kemessia
Publié: (2026)

Guaranteed Recovery of Unambiguous Clusters
par: Mazooji, Kayvon, et autres
Publié: (2025)

Online Learning with Unknown Constraints
par: Sridharan, Karthik, et autres
Publié: (2024)

Conformal Policy Control
par: Prinster, Drew, et autres
Publié: (2026)

Distributionally Robust Safety Verification of Neural Networks via Worst-Case CVaR
par: Kishida, Masako
Publié: (2025)

Finite-Time Analysis of MCTS in Continuous POMDP Planning
par: Kong, Da, et autres
Publié: (2026)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
par: Boudart, Pierre, et autres
Publié: (2026)

Generalization Bounds: Perspectives from Information Theory and PAC-Bayes
par: Hellström, Fredrik, et autres
Publié: (2023)

Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
par: Zhang, Bohan, et autres
Publié: (2025)

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
par: Chen, Fan, et autres
Publié: (2025)

From Thomas Bayes to Big Data: On the feasibility of being a subjective Bayesian
par: Ritov, Ya'acov
Publié: (2025)

No need for an oracle: the nonparametric maximum likelihood decision in the compound decision problem is minimax
par: Ritov, Ya'acov
Publié: (2023)

A mixture of a normal distribution with random mean and variance -- Examples of inconsistency of maximum likelihood estimates
par: Ritov, Ya'acov
Publié: (2024)

Tail-Aware Information-Theoretic Generalization for RLHF and SGLD
par: Zhang, Huiming, et autres
Publié: (2026)

A Diffusion Analysis of Policy Gradient for Stochastic Bandits
par: Lattimore, Tor
Publié: (2026)

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
par: Baharav, Tavor Z., et autres
Publié: (2025)

Risk Analysis and Design Against Adversarial Actions
par: Campi, Marco C., et autres
Publié: (2025)

Le Cam Distortion: A Decision-Theoretic Framework for Robust Transfer Learning
par: Akdemir, Deniz
Publié: (2025)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
par: Hao, Sai, et autres
Publié: (2026)

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
par: Yu, Lijia, et autres
Publié: (2025)

Conformal Risk Control
par: Angelopoulos, Anastasios N., et autres
Publié: (2022)