Imagen de Portada

Ergodicity in reinforcement learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Baumann, Dominik, Noorani, Erfaun, Mustafin, Arsenii, Sheng, Xinyi, Verbruggen, Bert, Vanhoyweghen, Arne, Ginis, Vincent, Schön, Thomas B.
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

Model-Agnostic Solutions for Deep Reinforcement Learning in Non-Ergodic Contexts
por: Verbruggen, Bert, et al.
Publicado: (2026)

Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
por: Mustafin, Arsenii, et al.
Publicado: (2025)

Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations
por: Baumann, Dominik, et al.
Publicado: (2023)

Safe reinforcement learning in uncertain contexts
por: Baumann, Dominik, et al.
Publicado: (2024)

Lexical Hints of Accuracy in LLM Reasoning Chains
por: Vanhoyweghen, Arne, et al.
Publicado: (2025)

Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning
por: Sheng, Xinyi, et al.
Publicado: (2025)

Distributed Risk-Sensitive Safety Filters for Uncertain Discrete-Time Systems
por: Lederer, Armin, et al.
Publicado: (2025)

Risk-Sensitive Reinforcement Learning with Exponential Criteria
por: Noorani, Erfaun, et al.
Publicado: (2022)

Metro 3 in Brussels under uncertainty: scenario-based public transport accessibility analysis
por: Verbeken, Brecht, et al.
Publicado: (2025)

On Value Iteration Convergence in Connected MDPs
por: Mustafin, Arsenii, et al.
Publicado: (2024)

Closing the gap between SVRG and TD-SVRG with Gradient Splitting
por: Mustafin, Arsenii, et al.
Publicado: (2022)

Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis
por: Liu, Rui, et al.
Publicado: (2024)

Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures
por: Noorani, Erfaun, et al.
Publicado: (2025)

Safe learning-based control via function-based uncertainty quantification
por: Tokmak, Abdullah, et al.
Publicado: (2026)

From Abstraction to Reality: DARPA's Vision for Robust Sim-to-Real Autonomy
por: Noorani, Erfaun, et al.
Publicado: (2025)

Analysis of Value Iteration Through Absolute Probability Sequences
por: Mustafin, Arsenii, et al.
Publicado: (2025)

Geometric Re-Analysis of Classical MDP Solving Algorithms
por: Mustafin, Arsenii, et al.
Publicado: (2025)

Towards safe control parameter tuning in distributed multi-agent systems
por: Tokmak, Abdullah, et al.
Publicado: (2025)

Safe Bayesian optimization across noise models via scenario programming
por: Tokmak, Abdullah, et al.
Publicado: (2025)

PACSBO: Probably approximately correct safe Bayesian optimization
por: Tokmak, Abdullah, et al.
Publicado: (2024)

MDP Geometry, Normalization and Reward Balancing Solvers
por: Mustafin, Arsenii, et al.
Publicado: (2024)

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
por: Hamman, Faisal, et al.
Publicado: (2023)

The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
por: Tori, Floriano, et al.
Publicado: (2024)

Safe exploration in reproducing kernel Hilbert spaces
por: Tokmak, Abdullah, et al.
Publicado: (2025)

The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer
por: Ballon, Marthe, et al.
Publicado: (2025)

Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs
por: Mobini, Melika, et al.
Publicado: (2026)

Probing the Trajectories of Reasoning Traces in Large Language Models
por: Ballon, Marthe, et al.
Publicado: (2026)

Estimating problem difficulty without ground truth using Large Language Model comparisons
por: Ballon, Marthe, et al.
Publicado: (2025)

A Rigorous, Tractable Measure of Model Complexity
por: Allerbo, Oskar, et al.
Publicado: (2026)

Is Supervised Learning Really That Different from Unsupervised?
por: Allerbo, Oskar, et al.
Publicado: (2025)

Flexible Counterfactual Explanations with Generative Models
por: Hellemans, Stig, et al.
Publicado: (2025)

Benchmarks Saturate When The Model Gets Smarter Than The Judge
por: Ballon, Marthe, et al.
Publicado: (2026)

Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers
por: Gokhale, Gargya, et al.
Publicado: (2024)

Operating critical machine learning models in resource constrained regimes
por: Selvan, Raghavendra, et al.
Publicado: (2023)

The hidden risks of temporal resampling in clinical reinforcement learning
por: Frost, Thomas, et al.
Publicado: (2026)

Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)
por: Verbeken, Brecht, et al.
Publicado: (2026)

Probing Graph Neural Network Activation Patterns Through Graph Topology
por: Tori, Floriano, et al.
Publicado: (2026)

Leveraging weights signals -- Predicting and improving generalizability in reinforcement learning
por: Moulin, Olivier, et al.
Publicado: (2025)

Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability
por: Deng, Mingwei, et al.
Publicado: (2025)

Multi-Round Human-AI Collaboration with User-Specified Requirements
por: Noorani, Sima, et al.
Publicado: (2026)