Imagen de Portada

On the geometry and topology of representations: the manifolds of modular addition

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Moisescu-Pareja, Gabriela, McCracken, Gavin, Wiltzer, Harley, Létourneau, Vincent, Daniels, Colin, Precup, Doina, Love, Jonathan
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

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
por: McCracken, Gavin, et al.
Publicado: (2025)

On the Privacy of Selection Mechanisms with Gaussian Noise
por: Lebensold, Jonathan, et al.
Publicado: (2024)

Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
por: Carr, Jonathan Colaço, et al.
Publicado: (2023)

Diversity-Enriched Option-Critic
por: Kamat, Anand, et al.
Publicado: (2020)

Functional Acceleration for Policy Mirror Descent
por: Chelu, Veronica, et al.
Publicado: (2024)

A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings
por: Alver, Safa, et al.
Publicado: (2022)

Tractable Representations for Convergent Approximation of Distributional HJB Equations
por: Alhosh, Julie, et al.
Publicado: (2025)

Balancing Plasticity and Stability with Fast and Slow Successor Features
por: Chua, Raymond, et al.
Publicado: (2026)

Foundations of Multivariate Distributional Reinforcement Learning
por: Wiltzer, Harley, et al.
Publicado: (2024)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
por: Arnob, Samin Yeasar, et al.
Publicado: (2025)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
por: Jain, Arushi, et al.
Publicado: (2024)

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
por: Alver, Safa, et al.
Publicado: (2024)

Relative Trajectory Balance is equivalent to Trust-PCL
por: Deleu, Tristan, et al.
Publicado: (2025)

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
por: Carr, Jonathan Colaço, et al.
Publicado: (2026)

Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
por: Jhaveri, Yash, et al.
Publicado: (2025)

Fluid-Agent Reinforcement Learning
por: Sharma, Shishir, et al.
Publicado: (2026)

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
por: Ishfaq, Haque, et al.
Publicado: (2025)

Parseval Regularization for Continual Reinforcement Learning
por: Chung, Wesley, et al.
Publicado: (2024)

Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
por: Wiltzer, Harley, et al.
Publicado: (2024)

Discrete Probabilistic Inference as Control in Multi-path Environments
por: Deleu, Tristan, et al.
Publicado: (2024)

Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
por: Zhang, Shuyuan, et al.
Publicado: (2025)

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
por: Rahn, Nate, et al.
Publicado: (2023)

KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
por: Zimmermann, Eric, et al.
Publicado: (2025)

Learning Successor Features the Simple Way
por: Chua, Raymond, et al.
Publicado: (2024)

QGFN: Controllable Greediness with Action Values
por: Lau, Elaine, et al.
Publicado: (2024)

Mitigating Downstream Model Risks via Model Provenance
por: Wang, Keyu, et al.
Publicado: (2024)

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
por: Patil, Gandharv, et al.
Publicado: (2022)

School Library Media Specialists' Perceptions of Practice and Importance of Roles Described in "Information Power".
por: McCracken, Anne
Publicado: (2001)

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
por: Jain, Arnav Kumar, et al.
Publicado: (2024)

Fairness in Reinforcement Learning with Bisimulation Metrics
por: Rezaei-Shoshtari, Sahand, et al.
Publicado: (2024)

Policy Gradient Methods in the Presence of Symmetries and State Abstractions
por: Panangaden, Prakash, et al.
Publicado: (2023)

Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
por: Luo, Ziyan, et al.
Publicado: (2025)

Capacity-Constrained Continual Learning
por: Wen, Zheng, et al.
Publicado: (2025)

Code as Reward: Empowering Reinforcement Learning with VLMs
por: Venuto, David, et al.
Publicado: (2024)

Affordances Enable Partial World Modeling with LLMs
por: Khetarpal, Khimya, et al.
Publicado: (2026)

Effective Protein-Protein Interaction Exploration with PPIretrieval
por: Hua, Chenqing, et al.
Publicado: (2024)

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
por: Zhao, Mingde, et al.
Publicado: (2023)

Rotation-Preserving Supervised Fine-Tuning
por: Jin, Hangzhan, et al.
Publicado: (2026)

A Distributional Analogue to the Successor Representation
por: Wiltzer, Harley, et al.
Publicado: (2024)

MUDiff: Unified Diffusion for Complete Molecule Generation
por: Hua, Chenqing, et al.
Publicado: (2023)