Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pigozzi, Federico, Levin, Michael
Format:	Preprint
Publié:	2026
Sujets:	Neural and Evolutionary Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Cancermorphic Computing Toward Multilevel Machine Intelligence
par: Moreddu, Rosalia, et autres
Publié: (2025)

Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels
par: Rentschler, Micah, et autres
Publié: (2026)

Causal Learning with Neural Assemblies
par: Kopadi, Evangelia, et autres
Publié: (2026)

Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks
par: Mészáros, Balázs, et autres
Publié: (2024)

Causal-Guided Dimension Reduction for Efficient Pareto Optimization
par: Jayasuriya, Dinithi, et autres
Publié: (2025)

Pruning as Evolution: Emergent Sparsity Through Selection Dynamics in Neural Networks
par: Shah, Zubair, et autres
Publié: (2026)

Emergent Collective Reproduction via Evolving Neuronal Flocks
par: Le, Nam H., et autres
Publié: (2024)

Causal Explanations from the Geometric Properties of ReLU Neural Networks
par: Woods, Hector, et autres
Publié: (2026)

Emergence of Implicit World Models from Mortal Agents
par: Horibe, Kazuya, et autres
Publié: (2024)

Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
par: Lin, Yuanguo, et autres
Publié: (2024)

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
par: Lv, Haoze, et autres
Publié: (2026)

Evolutionary Algorithms for Optimizing Emergency Exit Placement in Indoor Environments
par: Cotta, Carlos, et autres
Publié: (2024)

Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
par: O'Connor, Jim, et autres
Publié: (2025)

EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning
par: Zheng, Bowen, et autres
Publié: (2025)

Evolutionary Reinforcement Learning for Interpretable Decision-Making in Supply Chain Management
par: Genetti, Stefano, et autres
Publié: (2025)

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
par: Pes, Lorenzo, et autres
Publié: (2024)

Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning
par: Li, Ke, et autres
Publié: (2024)

Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning
par: Sun, Yinqian, et autres
Publié: (2025)

Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-objective Optimization
par: Shao, Shuai, et autres
Publié: (2026)

The Stacked Autoencoder Evolution Hypothesis
par: Iizuka, Hiroyuki
Publié: (2026)

Effective Predictive Modeling for Emergency Department Visits and Evaluating Exogenous Variables Impact: Using Explainable Meta-learning Gradient Boosting
par: Neshat, Mehdi, et autres
Publié: (2024)

Graph-Theoretic Measures for Interpretable Multicriteria Decision Making in Emergency Department Layout Optimization
par: Sarhan, Ola, et autres
Publié: (2025)

CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning
par: Xu, Zijie, et autres
Publié: (2025)

A Perturbation and Speciation-Based Algorithm for Dynamic Optimization Uninformed of Change
par: Signorelli, Federico, et autres
Publié: (2025)

Advanced Multimodal Learning for Seizure Detection and Prediction: Concept, Challenges, and Future Directions
par: Ahmad, Ijaz, et autres
Publié: (2026)

A Survey of Lottery Ticket Hypothesis
par: Liu, Bohan, et autres
Publié: (2024)

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

UAV-assisted Joint Mobile Edge Computing and Data Collection via Matching-enabled Deep Reinforcement Learning
par: Wang, Boxiong, et autres
Publié: (2025)

Brain-inspired Computational Modeling of Action Recognition with Recurrent Spiking Neural Networks Equipped with Reinforcement Delay Learning
par: Nadafian, Alireza, et autres
Publié: (2024)

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning
par: Sun, Geng, et autres
Publié: (2025)

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

Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model
par: Yang, Xu, et autres
Publié: (2025)

A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
par: Hazan, Hananel, et autres
Publié: (2026)

Diffusion Models are Evolutionary Algorithms
par: Zhang, Yanbo, et autres
Publié: (2024)

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

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks
par: Dong, Yiting, et autres
Publié: (2025)

Interpreting V1 Population Activity via Image-Neural Latent Representation Alignment
par: Wang, Xin, et autres
Publié: (2026)

Enes Causal Discovery
par: Kafantaris, Alexis
Publié: (2026)

Evolutionary Causal Discovery with Relative Impact Stratification for Interpretable Data Analysis
par: Deng, Ou, et autres
Publié: (2024)

MBL-CPDP: A Multi-objective Bilevel Method for Cross-Project Defect Prediction via Automated Machine Learning
par: Chen, Jiaxin, et autres
Publié: (2024)