Imagen de Portada

Spectral Bellman Method: Unifying Representation and Exploration in RL

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nabati, Ofir, Dai, Bo, Mannor, Shie, Tennenholtz, Guy
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Representation-Driven Reinforcement Learning
por: Nabati, Ofir, et al.
Publicado: (2023)

Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
por: Cohen, Lior, et al.
Publicado: (2026)

Conservative DDPG -- Pessimistic RL without Ensemble
por: Soffair, Nitsan, et al.
Publicado: (2024)

MinMaxMin $Q$-learning
por: Soffair, Nitsan, et al.
Publicado: (2024)

Representative Action Selection for Large Action Space: From Bandits to MDPs
por: Zhou, Quan, et al.
Publicado: (2025)

Spectral Souping: A Unified Framework for Online Preference Alignment
por: Chow, Yinlam, et al.
Publicado: (2026)

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
por: Kwon, Jeongyeol, et al.
Publicado: (2024)

Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels
por: Perets, Binyamin, et al.
Publicado: (2026)

Efficient Fairness-Performance Pareto Front Computation
por: Kozdoba, Mark, et al.
Publicado: (2024)

The Value of Mechanistic Priors in Sequential Decision Making
por: Shufaro, Itai, et al.
Publicado: (2026)

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
por: Gadot, Uri, et al.
Publicado: (2025)

Sobolev Space Regularised Pre Density Models
por: Kozdoba, Mark, et al.
Publicado: (2023)

Representative Action Selection for Large Action Space Bandit Families
por: Zhou, Quan, et al.
Publicado: (2025)

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
por: Du, Yihan, et al.
Publicado: (2024)

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

On Bits and Bandits: Quantifying the Regret-Information Trade-off
por: Shufaro, Itai, et al.
Publicado: (2024)

Preference Adaptive and Sequential Text-to-Image Generation
por: Nabati, Ofir, et al.
Publicado: (2024)

Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
por: Vainshtein, Ron, et al.
Publicado: (2025)

Generalizable and Robust Spectral Method for Multi-view Representation Learning
por: Yacobi, Amitai, et al.
Publicado: (2024)

Improving Token-Based World Models with Parallel Observation Prediction
por: Cohen, Lior, et al.
Publicado: (2024)

Tree Search-Based Policy Optimization under Stochastic Execution Delay
por: Valensi, David, et al.
Publicado: (2024)

Reinforcement Learning with Segment Feedback
por: Du, Yihan, et al.
Publicado: (2025)

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
por: Wang, Kaixin, et al.
Publicado: (2023)

SQT -- std $Q$-target
por: Soffair, Nitsan, et al.
Publicado: (2024)

On the Convergence of Single-Timescale Actor-Critic
por: Kumar, Navdeep, et al.
Publicado: (2024)

Simulus: Combining Improvements in Sample-Efficient World Model Agents
por: Cohen, Lior, et al.
Publicado: (2025)

Policy Gradient with Tree Expansion
por: Dalal, Gal, et al.
Publicado: (2023)

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
por: Liang, Anthony, et al.
Publicado: (2024)

Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators
por: Linial, Ori, et al.
Publicado: (2024)

Bayesian Regret Minimization in Offline Bandits
por: Petrik, Marek, et al.
Publicado: (2023)

VLM-Guided Experience Replay
por: Sharony, Elad, et al.
Publicado: (2026)

State Entropy Regularization for Robust Reinforcement Learning
por: Ashlag, Yonatan, et al.
Publicado: (2025)

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
por: Gadot, Uri, et al.
Publicado: (2023)

Adversarial Bandit over Bandits: Hierarchical Bandits for Online Configuration Management
por: Avin, Chen, et al.
Publicado: (2025)

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
por: Yang, Tong, et al.
Publicado: (2025)

Deterministic Exploration via Stationary Bellman Error Maximization
por: Griesbach, Sebastian, et al.
Publicado: (2024)

Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead
por: Koren, Uri, et al.
Publicado: (2025)

On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes
por: Kumar, Navdeep, et al.
Publicado: (2024)

Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum
por: Kumar, Navdeep, et al.
Publicado: (2026)

Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
por: Luo, Qin-Wen, et al.
Publicado: (2025)