Imagen de Portada

Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lazzati, Filippo, Mutti, Mirco, Metelli, Alberto Maria
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
por: Lazzati, Filippo, et al.
Publicado: (2024)

Reward Compatibility: A Framework for Inverse RL
por: Lazzati, Filippo, et al.
Publicado: (2025)

Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
por: Lazzati, Filippo, et al.
Publicado: (2025)

Learning Utilities from Demonstrations in Markov Decision Processes
por: Lazzati, Filippo, et al.
Publicado: (2024)

Robustness in the Face of Partial Identifiability in Reward Learning
por: Lazzati, Filippo, et al.
Publicado: (2025)

Imitation Learning as Return Distribution Matching
por: Lazzati, Filippo, et al.
Publicado: (2025)

A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning
por: Drappo, Gianluca, et al.
Publicado: (2024)

Test-Time Regret Minimization in Meta Reinforcement Learning
por: Mutti, Mirco, et al.
Publicado: (2024)

Rising Rested Bandits: Lower Bounds and Efficient Algorithms
por: Fiandri, Marco, et al.
Publicado: (2024)

Performance Improvement Bounds for Lipschitz Configurable Markov Decision Processes
por: Metelli, Alberto Maria
Publicado: (2024)

Thompson Sampling-like Algorithms for Stochastic Rising Bandits
por: Fiandri, Marco, et al.
Publicado: (2025)

Inverse Reinforcement Learning with Sub-optimal Experts
por: Poiani, Riccardo, et al.
Publicado: (2024)

Towards Principled Unsupervised Multi-Agent Reinforcement Learning
por: Zamboni, Riccardo, et al.
Publicado: (2025)

Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL
por: Zhang, Weitong, et al.
Publicado: (2021)

Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting
por: Russo, Alessio, et al.
Publicado: (2024)

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
por: Zamboni, Riccardo, et al.
Publicado: (2024)

A Classification View on Meta Learning Bandits
por: Mutti, Mirco, et al.
Publicado: (2025)

Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
por: Gupta, Aaryan, et al.
Publicado: (2025)

Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story
por: De Paola, Vincenzo, et al.
Publicado: (2025)

K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents
por: De Paola, Vincenzo, et al.
Publicado: (2026)

Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
por: Li, Shangzhe, et al.
Publicado: (2026)

A Theoretical Framework for Partially Observed Reward-States in RLHF
por: Kausik, Chinmaya, et al.
Publicado: (2024)

How to Explore with Belief: State Entropy Maximization in POMDPs
por: Zamboni, Riccardo, et al.
Publicado: (2024)

From Parameters to Behaviors: Unsupervised Compression of the Policy Space
por: Tenedini, Davide, et al.
Publicado: (2025)

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
por: Sun, Hao, et al.
Publicado: (2023)

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
por: Francis-Meretzki, Shelly, et al.
Publicado: (2026)

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
por: Yue, Bo, et al.
Publicado: (2024)

Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
por: Dronen, Nicholas, et al.
Publicado: (2025)

One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
por: Chen, Elynn, et al.
Publicado: (2026)

Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis
por: Bonetti, Paolo, et al.
Publicado: (2024)

Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards
por: Mussi, Marco, et al.
Publicado: (2024)

Sliding-Window Thompson Sampling for Non-Stationary Settings
por: Fiandri, Marco, et al.
Publicado: (2024)

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

Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds
por: Metelli, Alberto Maria, et al.
Publicado: (2025)

Pure Exploration under Mediators' Feedback
por: Poiani, Riccardo, et al.
Publicado: (2023)

A Refined Analysis of UCBVI
por: Drago, Simone, et al.
Publicado: (2025)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
por: Mutti, Mirco, et al.
Publicado: (2023)

Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
por: Huang, Ruiquan, et al.
Publicado: (2025)

MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search
por: Kim, Sungyoon, et al.
Publicado: (2025)

An Empirical Risk Minimization Approach for Offline Inverse RL and Dynamic Discrete Choice Model
por: Kang, Enoch H., et al.
Publicado: (2025)