:: Library Catalog

Íomhá chlúdaigh

Sábháilte in:

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Maran, Davide, Restelli, Marcello
Formáid:	Preprint
Foilsithe / Cruthaithe:	2026
Ábhair:	Machine Learning
Rochtain ar líne:	https://arxiv.org/abs/2605.19584
Clibeanna:	Cuir clib leis Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

Míreanna comhchosúla

Finite Sample Bounds for Non-Parametric Regression: Optimal Sample Efficiency and Space Complexity
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2024)

Learning in Markov Decision Processes with Exogenous Dynamics
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2026)

Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2024)

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2024)

Online Dynamic Pricing of Complementary Products
de réir: Mussi, Marco, et al.
Foilsithe / Cruthaithe: (2025)

Autoregressive Bandits
de réir: Bacchiocchi, Francesco, et al.
Foilsithe / Cruthaithe: (2022)

A Reinforcement Learning Approach for Optimal Control in Microgrids
de réir: Salaorni, Davide, et al.
Foilsithe / Cruthaithe: (2025)

From Parameters to Behaviors: Unsupervised Compression of the Policy Space
de réir: Tenedini, Davide, et al.
Foilsithe / Cruthaithe: (2025)

No-Regret Reinforcement Learning in Smooth MDPs
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2024)

Sharper Guarantees for Misspecified Kernelized Bandit Optimization
de réir: Maran, Davide, et al.
Foilsithe / Cruthaithe: (2026)

Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information
de réir: Zamboni, Riccardo, et al.
Foilsithe / Cruthaithe: (2025)

"So, Tell Me About Your Policy...": Distillation of interpretable policies from Deep Reinforcement Learning agents
de réir: Dispoto, Giovanni, et al.
Foilsithe / Cruthaithe: (2025)

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching
de réir: Fraschini, Andrea, et al.
Foilsithe / Cruthaithe: (2026)

Sharing Knowledge in Multi-Task Deep Reinforcement Learning
de réir: D'Eramo, Carlo, et al.
Foilsithe / Cruthaithe: (2024)

How Log-Barrier Helps Exploration in Policy Optimization
de réir: Cesani, Leonardo, et al.
Foilsithe / Cruthaithe: (2026)

Towards Principled Unsupervised Multi-Agent Reinforcement Learning
de réir: Zamboni, Riccardo, et al.
Foilsithe / Cruthaithe: (2025)

Building surrogate models using trajectories of agents trained by Reinforcement Learning
de réir: Cestero, Julen, et al.
Foilsithe / Cruthaithe: (2025)

Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models
de réir: Russo, Alessio, et al.
Foilsithe / Cruthaithe: (2025)

Pure Exploration under Mediators' Feedback
de réir: Poiani, Riccardo, et al.
Foilsithe / Cruthaithe: (2023)

Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis
de réir: Bonetti, Paolo, et al.
Foilsithe / Cruthaithe: (2024)

Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting
de réir: Russo, Alessio, et al.
Foilsithe / Cruthaithe: (2024)

A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning
de réir: Drappo, Gianluca, et al.
Foilsithe / Cruthaithe: (2024)

State and Action Factorization in Power Grids
de réir: Losapio, Gianvito, et al.
Foilsithe / Cruthaithe: (2024)

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
de réir: Zamboni, Riccardo, et al.
Foilsithe / Cruthaithe: (2024)

K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents
de réir: De Paola, Vincenzo, et al.
Foilsithe / Cruthaithe: (2026)

How to Explore with Belief: State Entropy Maximization in POMDPs
de réir: Zamboni, Riccardo, et al.
Foilsithe / Cruthaithe: (2024)

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
de réir: Poiani, Riccardo, et al.
Foilsithe / Cruthaithe: (2024)

Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story
de réir: De Paola, Vincenzo, et al.
Foilsithe / Cruthaithe: (2025)

Policy Gradient with Active Importance Sampling
de réir: Papini, Matteo, et al.
Foilsithe / Cruthaithe: (2024)

Information Capacity Regret Bounds for Bandits with Mediator Feedback
de réir: Eldowa, Khaled, et al.
Foilsithe / Cruthaithe: (2024)

Statistical Analysis of Policy Space Compression Problem
de réir: Molaei, Majid, et al.
Foilsithe / Cruthaithe: (2024)

Inverse Reinforcement Learning with Sub-optimal Experts
de réir: Poiani, Riccardo, et al.
Foilsithe / Cruthaithe: (2024)

Actor-Critic with Active Importance Sampling
de réir: Molaei, Majid, et al.
Foilsithe / Cruthaithe: (2026)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
de réir: Mutti, Mirco, et al.
Foilsithe / Cruthaithe: (2023)

Power Grid Control with Graph-Based Distributed Reinforcement Learning
de réir: Fabrizio, Carlo, et al.
Foilsithe / Cruthaithe: (2025)

Optimal Multi-Fidelity Best-Arm Identification
de réir: Poiani, Riccardo, et al.
Foilsithe / Cruthaithe: (2024)

Best Arm Identification for Stochastic Rising Bandits
de réir: Mussi, Marco, et al.
Foilsithe / Cruthaithe: (2023)

Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
de réir: Cestero, Julen, et al.
Foilsithe / Cruthaithe: (2025)

Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks
de réir: Cestero, Julen, et al.
Foilsithe / Cruthaithe: (2025)

Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting
de réir: Genalti, Gianmarco, et al.
Foilsithe / Cruthaithe: (2024)