Copertina

On the instability of local learning algorithms: Q-learning can fail in infinite state spaces

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ayesta, Urtzi, Foss, Sergey, Jonckheere, Matthieu, Puricelli, Vittorio
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Decision-Epoch Matters: Unveiling its Impact on the Stability of Scheduling with Randomly Varying Connectivity
di: Soprano-Loto, Nahuel, et al.
Pubblicazione: (2024)

On the Age of Information in Single-Server Queues with Aged Updates
di: Miguelez, Fernando, et al.
Pubblicazione: (2025)

Deep reinforcement learning for weakly coupled MDP's with continuous actions
di: Robledo, Francisco, et al.
Pubblicazione: (2024)

$K-$means with learned metrics
di: Groisman, Pablo, et al.
Pubblicazione: (2026)

Online matching for the multiclass stochastic block model
di: Soprano-Loto, Nahuel, et al.
Pubblicazione: (2023)

Gaussian Approximation for Asynchronous Q-learning
di: Rubtsov, Artemy, et al.
Pubblicazione: (2026)

Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach
di: Alahyane, Abdelkrim, et al.
Pubblicazione: (2026)

Waves Everywhere: A Distributional Equation Approach to Front Propagation
di: Jonckheere, Matthieu, et al.
Pubblicazione: (2026)

Efficiency of Parallel and Restart Exploration Strategies in Model Free Stochastic Simulations
di: Garcia, Ernesto, et al.
Pubblicazione: (2025)

On Recurrence of the Infinite Server Queue
di: Foss, Sergey, et al.
Pubblicazione: (2025)

Compressibility and Stochastic Stability of Monotone Markov Chain
di: Foss, Sergey, et al.
Pubblicazione: (2024)

Maxima over random time intervals for heavy-tailed compound renewal and Lévy processes
di: Foss, Sergey, et al.
Pubblicazione: (2023)

Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency
di: Alahyane, Abdelkrim, et al.
Pubblicazione: (2025)

Efficient Remote Monitoring through Noisy Random Access with Retransmissions
di: Foss, Sergey, et al.
Pubblicazione: (2025)

Last passage percolation and limit theorems in Barak-Erdős directed random graphs and related models
di: Foss, Sergey, et al.
Pubblicazione: (2023)

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
di: Comte, Céline, et al.
Pubblicazione: (2023)

Any random variable with right-unbounded distributional support is the minimum of independent and very heavy-tailed random variables
di: Foss, Sergey, et al.
Pubblicazione: (2025)

Only Segmented Heavy Tails Can Produce a Light-Tailed Minimum
di: Foss, Sergey, et al.
Pubblicazione: (2026)

Heavy-tail asymptotics for the length of a busy period in a Generalised Jackson Network
di: Foss, Sergey, et al.
Pubblicazione: (2025)

Critical non-local spatial branching processes with infinite variance conditioned on survival
di: Cardona-Tobón, Natalia, et al.
Pubblicazione: (2025)

Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms
di: Valleti, Mani, et al.
Pubblicazione: (2024)

Reflected stochastic partial differential equations with fully local monotone coefficients in infinite dimensional domains
di: Li, Qi, et al.
Pubblicazione: (2026)

Deep learning based numerical approximation algorithms for stochastic partial differential equations
di: Beck, Christian, et al.
Pubblicazione: (2020)

Optimal distributions for randomized unbiased estimators with an infinite horizon and an adaptive algorithm
di: Zheng, Chao, et al.
Pubblicazione: (2023)

Markov branching process with infinite variance and non-homogeneous immigration with infinite mean
di: Mitov, Kosto V., et al.
Pubblicazione: (2025)

Quasi-stationary distributions in reducible state spaces
di: Champagnat, Nicolas, et al.
Pubblicazione: (2022)

Robust $Q$-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty
di: Neufeld, Ariel, et al.
Pubblicazione: (2022)

Singular mean-field backward stochastic Volterra integral equations in infinite dimensional spaces
di: Asadzade, Javad A., et al.
Pubblicazione: (2024)

The suprema of infinitely divisible processes
di: Bednorz, Witold, et al.
Pubblicazione: (2020)

What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture
di: Chang, Heng-Sheng, et al.
Pubblicazione: (2025)

Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy
di: Appel, Jan, et al.
Pubblicazione: (2026)

Sublinear expectation structure under countable state space
di: Yang, Shuzhen, et al.
Pubblicazione: (2024)

Simulation of infinite-dimensional diffusion bridges
di: Pieper-Sethmacher, Thorben, et al.
Pubblicazione: (2025)

On the accuracy of the poissonisation in the infinite occupancy scheme
di: Chebunin, Mikhail
Pubblicazione: (2017)

Riesz transform, function spaces and their applications on infinite dimensional compact groups
di: Bendikov, Alexander, et al.
Pubblicazione: (2025)

Deep learning algorithms for FBSDEs with jumps: Applications to option pricing and a MFG model for smart grids
di: Alasseur, Clémence, et al.
Pubblicazione: (2024)

Augmenting chemical databases for atomistic machine learning by sampling conformational space
di: Vazquez-Salazar, Luis Itza, et al.
Pubblicazione: (2025)

Machine learning approach to detect dynamical states from recurrence measures
di: Thakur, Dheeraja, et al.
Pubblicazione: (2024)

Guided filtering and smoothing for infinite-dimensional diffusions
di: Pieper-Sethmacher, Thorben, et al.
Pubblicazione: (2025)

Exponential growth of random infinite Fibonacci sequences
di: Goldsheid, Ilya, et al.
Pubblicazione: (2025)