Imagen de Portada

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Elliott, Chris, Urdshals, Einar, Quarel, David, Farrugia-Roberts, Matthew, Murfet, Daniel
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Interpreting Reinforcement Learning Agents with Susceptibilities
por: Elliott, Chris, et al.
Publicado: (2026)

Loss Landscape Degeneracy and Stagewise Development in Transformers
por: Hoogland, Jesse, et al.
Publicado: (2024)

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
por: Urdshals, Einar, et al.
Publicado: (2025)

Structure Development in List-Sorting Transformers
por: Urdshals, Einar, et al.
Publicado: (2025)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
por: Elliott, Chris, et al.
Publicado: (2026)

Dynamics of Transient Structure in In-Context Linear Regression Transformers
por: Carroll, Liam, et al.
Publicado: (2025)

Linear Response Estimators for Singular Statistical Models
por: Elliott, Chris, et al.
Publicado: (2026)

Structure and Scale in Simplicial Sequence Modelling
por: Farrugia-Roberts, Matthew
Publicado: (2026)

Proximity to Losslessly Compressible Parameters
por: Farrugia-Roberts, Matthew
Publicado: (2023)

Mitigating Goal Misgeneralization via Minimax Regret
por: Sadek, Karim Abdel, et al.
Publicado: (2025)

Modes of Sequence Models and Learning Coefficients
por: Chen, Zhongtian, et al.
Publicado: (2025)

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
por: Lehalleur, Simon Pepin, et al.
Publicado: (2025)

Influence Dynamics and Stagewise Data Attribution
por: Lee, Jin Hwa, et al.
Publicado: (2025)

Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks
por: Benito-Rodriguez, Éloïse, et al.
Publicado: (2025)

Patterning: The Dual of Interpretability
por: Wang, George, et al.
Publicado: (2026)

Programs as Singularities
por: Murfet, Daniel, et al.
Publicado: (2025)

Stagewise Boosting Distributional Regression
por: Wetscher, Mattias, et al.
Publicado: (2024)

Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning
por: Hüyük, Alihan, et al.
Publicado: (2024)

Dark Matter-induced electron excitations in silicon and germanium with Deep Learning
por: Catena, Riccardo, et al.
Publicado: (2024)

Regret-Based Defense in Adversarial Reinforcement Learning
por: Belaire, Roman, et al.
Publicado: (2023)

Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling
por: Aswadi, Afiq Abdillah Effiezal, et al.
Publicado: (2026)

Efficient Stagewise Pretraining via Progressive Subnetworks
por: Panigrahi, Abhishek, et al.
Publicado: (2024)

Majorization-Minimization Dual Stagewise Algorithm for Generalized Lasso
por: Chen, Jianmin, et al.
Publicado: (2025)

No-Regret Reinforcement Learning in Smooth MDPs
por: Maran, Davide, et al.
Publicado: (2024)

Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization
por: Kim, Chanyeong, et al.
Publicado: (2024)

Structural Inference: Interpreting Small Language Models with Susceptibilities
por: Baker, Garrett, et al.
Publicado: (2025)

Embryology of a Language Model
por: Wang, George, et al.
Publicado: (2025)

Logarithmic Regret for Online KL-Regularized Reinforcement Learning
por: Zhao, Heyang, et al.
Publicado: (2025)

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

SCALAR: Benchmarking SAE Interaction Sparsity in Toy LLMs
por: Fillingham, Sean P., et al.
Publicado: (2025)

Regret-Free Reinforcement Learning for LTL Specifications
por: Majumdar, Rupak, et al.
Publicado: (2024)

Tail Distribution of Regret in Optimistic Reinforcement Learning
por: Khodadadian, Sajad, et al.
Publicado: (2025)

Reinforcement Learning and Regret Bounds for Admission Control
por: Weber, Lucas, et al.
Publicado: (2024)

Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning
por: Chen, Zijun, et al.
Publicado: (2026)

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
por: Chen, Baiyuan, et al.
Publicado: (2025)

Symbolic State Partitioning for Reinforcement Learning
por: Ghaffari, Mohsen, et al.
Publicado: (2024)

Transfer in Reinforcement Learning via Regret Bounds for Learning Agents
por: Tuynman, Adrienne, et al.
Publicado: (2022)

Kernelized Reinforcement Learning with Order Optimal Regret Bounds
por: Vakili, Sattar, et al.
Publicado: (2023)

Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning
por: Lee, Harin, et al.
Publicado: (2026)

Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences
por: Shi, Ming, et al.
Publicado: (2026)