Image de couverture de livre

On the Importance of Multistability for Horizon Generalization in Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bakija, Asad, De Geeter, Florent, Brandoit, Julien, Sacré, Pierre, Drion, Guillaume
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Spike-based computation using classical recurrent neural networks
par: De Geeter, Florent, et autres
Publié: (2023)

Parallelizable memory recurrent units
par: De Geeter, Florent, et autres
Publié: (2026)

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
par: Brandoit, Julien, et autres
Publié: (2026)

Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
par: Brandoit, Julien, et autres
Publié: (2025)

Energy-Efficient Implementation of Spiking Recurrent Cells on FPGA
par: Harmeling, Pascal, et autres
Publié: (2026)

Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
par: Fyon, Arthur, et autres
Publié: (2026)

Context-dependent manifold learning: A neuromodulated constrained autoencoder approach
par: Adriaens, Jérôme, et autres
Publié: (2026)

Inward rectifier potassium channels interact with calcium channels to promote robust and physiological bistability
par: De Worm, Anaëlle, et autres
Publié: (2024)

Neuromodulation supports robust rhythmic pattern transitions in degenerate central pattern generators with fixed connectivity
par: Fyon, Arthur, et autres
Publié: (2026)

Dimensionality reduction of neuronal degeneracy reveals two interfering physiological mechanisms
par: Fyon, Arthur, et autres
Publié: (2024)

Horizon Generalization in Reinforcement Learning
par: Myers, Vivek, et autres
Publié: (2025)

Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
par: Ni, Tianwei, et autres
Publié: (2025)

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
par: Arnaboldi, Luca, et autres
Publié: (2024)

Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces
par: Angiuli, Andrea, et autres
Publié: (2023)

Stochastic Decision Horizons for Constrained Reinforcement Learning
par: Milosevic, Nikola, et autres
Publié: (2026)

Inverse Reinforcement Learning with Multiple Planning Horizons
par: Yao, Jiayu, et autres
Publié: (2024)

FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet
par: Pautrel, Thibault, et autres
Publié: (2026)

Effective Reward Specification in Deep Reinforcement Learning
par: Roy, Julien
Publié: (2024)

On the Effective Horizon of Inverse Reinforcement Learning
par: Xu, Yiqing, et autres
Publié: (2023)

Horizon Reduction as Information Loss in Offline Reinforcement Learning
par: Nidadala, Uday Kumar, et autres
Publié: (2025)

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning
par: Zhao, Hanye, et autres
Publié: (2024)

Reinforcement Learning with Random Time Horizons
par: Borrell, Enric Ribera, et autres
Publié: (2025)

Offline Reinforcement Learning with Universal Horizon Models
par: Chung, Hojun, et autres
Publié: (2026)

Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning
par: McInroe, Trevor, et autres
Publié: (2022)

Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings
par: Shi, C., et autres
Publié: (2020)

Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks
par: Yu, Yang
Publié: (2025)

Reinforcement Learning for Long-Horizon Interactive LLM Agents
par: Chen, Kevin, et autres
Publié: (2025)

Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
par: Pranger, Stefan, et autres
Publié: (2024)

Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning
par: Moulin, Antoine, et autres
Publié: (2025)

Beyond Distribution Sharpening: The Importance of Task Rewards
par: Mittal, Sarthak, et autres
Publié: (2026)

Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation
par: Park, Jaehyun, et autres
Publié: (2024)

Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning
par: Kar, Avik, et autres
Publié: (2024)

Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning
par: Zhang, Mingliang, et autres
Publié: (2024)

Model-Free versus Model-Based Reinforcement Learning for Fixed-Wing UAV Attitude Control Under Varying Wind Conditions
par: Olivares, David, et autres
Publié: (2024)

Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis
par: F, Clifford, et autres
Publié: (2025)

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
par: Audiffren, Julien, et autres
Publié: (2026)

Multistability of Self-Attention Dynamics in Transformers
par: Altafini, Claudio
Publié: (2025)

A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation
par: Scarponi, Valentina, et autres
Publié: (2024)

Random Policy Enables In-Context Reinforcement Learning within Trust Horizons
par: Chen, Weiqin, et autres
Publié: (2024)

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
par: Dai, Juntao, et autres
Publié: (2024)