Imagen de Portada

The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pigozzi, Federico, Levin, Michael
Formato:	Preprint
Publicado:	2026
Materias:	Neural and Evolutionary Computing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Cancermorphic Computing Toward Multilevel Machine Intelligence
por: Moreddu, Rosalia, et al.
Publicado: (2025)

Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels
por: Rentschler, Micah, et al.
Publicado: (2026)

Causal Learning with Neural Assemblies
por: Kopadi, Evangelia, et al.
Publicado: (2026)

Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks
por: Mészáros, Balázs, et al.
Publicado: (2024)

Causal-Guided Dimension Reduction for Efficient Pareto Optimization
por: Jayasuriya, Dinithi, et al.
Publicado: (2025)

Pruning as Evolution: Emergent Sparsity Through Selection Dynamics in Neural Networks
por: Shah, Zubair, et al.
Publicado: (2026)

Emergent Collective Reproduction via Evolving Neuronal Flocks
por: Le, Nam H., et al.
Publicado: (2024)

Causal Explanations from the Geometric Properties of ReLU Neural Networks
por: Woods, Hector, et al.
Publicado: (2026)

Emergence of Implicit World Models from Mortal Agents
por: Horibe, Kazuya, et al.
Publicado: (2024)

Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
por: Lin, Yuanguo, et al.
Publicado: (2024)

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
por: Lv, Haoze, et al.
Publicado: (2026)

Evolutionary Algorithms for Optimizing Emergency Exit Placement in Indoor Environments
por: Cotta, Carlos, et al.
Publicado: (2024)

Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
por: O'Connor, Jim, et al.
Publicado: (2025)

EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning
por: Zheng, Bowen, et al.
Publicado: (2025)

Evolutionary Reinforcement Learning for Interpretable Decision-Making in Supply Chain Management
por: Genetti, Stefano, et al.
Publicado: (2025)

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
por: Pes, Lorenzo, et al.
Publicado: (2024)

Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning
por: Li, Ke, et al.
Publicado: (2024)

Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning
por: Sun, Yinqian, et al.
Publicado: (2025)

Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-objective Optimization
por: Shao, Shuai, et al.
Publicado: (2026)

Effective Predictive Modeling for Emergency Department Visits and Evaluating Exogenous Variables Impact: Using Explainable Meta-learning Gradient Boosting
por: Neshat, Mehdi, et al.
Publicado: (2024)

The Stacked Autoencoder Evolution Hypothesis
por: Iizuka, Hiroyuki
Publicado: (2026)

Graph-Theoretic Measures for Interpretable Multicriteria Decision Making in Emergency Department Layout Optimization
por: Sarhan, Ola, et al.
Publicado: (2025)

CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning
por: Xu, Zijie, et al.
Publicado: (2025)

A Perturbation and Speciation-Based Algorithm for Dynamic Optimization Uninformed of Change
por: Signorelli, Federico, et al.
Publicado: (2025)

Advanced Multimodal Learning for Seizure Detection and Prediction: Concept, Challenges, and Future Directions
por: Ahmad, Ijaz, et al.
Publicado: (2026)

On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($λ$,$λ$))-GA
por: Nguyen, Tai, et al.
Publicado: (2025)

A Survey of Lottery Ticket Hypothesis
por: Liu, Bohan, et al.
Publicado: (2024)

UAV-assisted Joint Mobile Edge Computing and Data Collection via Matching-enabled Deep Reinforcement Learning
por: Wang, Boxiong, et al.
Publicado: (2025)

Brain-inspired Computational Modeling of Action Recognition with Recurrent Spiking Neural Networks Equipped with Reinforcement Delay Learning
por: Nadafian, Alireza, et al.
Publicado: (2024)

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning
por: Sun, Geng, et al.
Publicado: (2025)

Continual Learning with Hebbian Plasticity in Sparse and Predictive Coding Networks: A Survey and Perspective
por: Safa, Ali
Publicado: (2024)

Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model
por: Yang, Xu, et al.
Publicado: (2025)

A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
por: Hazan, Hananel, et al.
Publicado: (2026)

Diffusion Models are Evolutionary Algorithms
por: Zhang, Yanbo, et al.
Publicado: (2024)

Recovering Sparse Neural Connectivity from Partial Measurements: A Covariance-Based Approach with Granger-Causality Refinement
por: Simeon, Quilee
Publicado: (2026)

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks
por: Dong, Yiting, et al.
Publicado: (2025)

Interpreting V1 Population Activity via Image-Neural Latent Representation Alignment
por: Wang, Xin, et al.
Publicado: (2026)

Enes Causal Discovery
por: Kafantaris, Alexis
Publicado: (2026)

Evolutionary Causal Discovery with Relative Impact Stratification for Interpretable Data Analysis
por: Deng, Ou, et al.
Publicado: (2024)

MBL-CPDP: A Multi-objective Bilevel Method for Cross-Project Defect Prediction via Automated Machine Learning
por: Chen, Jiaxin, et al.
Publicado: (2024)