Image de couverture de livre

Learning to Reason Efficiently with Discounted Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ayoub, Alex, Asadi, Kavosh, Schuurmans, Dale, Szepesvári, Csaba, Bouyarmane, Karim
Format:	Preprint
Publié:	2025
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

Rectifying Regression in Reinforcement Learning
par: Ayoub, Alex, et autres
Publié: (2025)

Adjoint sharding for very long context training of state space models
par: Xu, Xingzi, et autres
Publié: (2025)

Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits
par: Liu, Shuai, et autres
Publié: (2026)

Exploration via linearly perturbed loss minimisation
par: Janz, David, et autres
Publié: (2023)

Ordering-based Conditions for Global Convergence of Policy Gradient Methods
par: Mei, Jincheng, et autres
Publié: (2025)

Stochastic Gradient Succeeds for Bandits
par: Mei, Jincheng, et autres
Publié: (2024)

Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning
par: Ayoub, Alex, et autres
Publié: (2024)

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$-Realizability and Concentrability
par: Tkachuk, Volodymyr, et autres
Publié: (2024)

Eluder dimension: localise it!
par: Bakhtiari, Alireza, et autres
Publié: (2026)

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
par: Liu, Shuai, et autres
Publié: (2024)

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
par: Mei, Jincheng, et autres
Publié: (2025)

C2-DPO: Constrained Controlled Direct Preference Optimization
par: Asadi, Kavosh, et autres
Publié: (2025)

Plastic Learning with Deep Fourier Features
par: Lewandowski, Alex, et autres
Publié: (2024)

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
par: Zhang, Hongming, et autres
Publié: (2023)

Sharper Guarantees for Misspecified Kernelized Bandit Optimization
par: Maran, Davide, et autres
Publié: (2026)

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
par: György, András, et autres
Publié: (2025)

LACONIC: Length-Aware Constrained Reinforcement Learning for LLM
par: Liu, Chang, et autres
Publié: (2026)

Learning the Target Network in Function Space
par: Asadi, Kavosh, et autres
Publié: (2024)

Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning
par: Dai, Bo, et autres
Publié: (2026)

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
par: Lin, Max Qiushi, et autres
Publié: (2025)

Spectral Representation-based Reinforcement Learning
par: Gao, Chenxiao, et autres
Publié: (2025)

Sharp analysis of linear ensemble sampling
par: Akhavan, Arya, et autres
Publié: (2026)

Reinforcement Teaching
par: Muslimani, Calarina, et autres
Publié: (2022)

Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences
par: Pipano, Idan, et autres
Publié: (2026)

Balancing optimism and pessimism in offline-to-online learning
par: Sentenac, Flore, et autres
Publié: (2025)

Ensemble sampling for linear bandits: small ensembles suffice
par: Janz, David, et autres
Publié: (2023)

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs
par: Tian, Tian, et autres
Publié: (2024)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
par: Zhong, Han, et autres
Publié: (2021)

Toward Understanding In-context vs. In-weight Learning
par: Chan, Bryan, et autres
Publié: (2024)

Rethinking the Foundations for Continual Reinforcement Learning
par: Elelimy, Esraa, et autres
Publié: (2025)

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off
par: Zhang, Zichen, et autres
Publié: (2022)

Reinforcement Learning with Quasi-Hyperbolic Discounting
par: Eshwar, S. R., et autres
Publié: (2024)

Learning Continually by Spectral Regularization
par: Lewandowski, Alex, et autres
Publié: (2024)

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
par: Liu, Zuxin, et autres
Publié: (2023)

Directions of Curvature as an Explanation for Loss of Plasticity
par: Lewandowski, Alex, et autres
Publié: (2023)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
par: Malek, Alan, et autres
Publié: (2025)

Bridging the Gap Between Average and Discounted TD Learning
par: Tian, Haoxing, et autres
Publié: (2026)

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
par: Thoppe, Gugan, et autres
Publié: (2026)

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting
par: Moghimi, Mehrdad, et autres
Publié: (2026)

Regret Minimization via Saddle Point Optimization
par: Kirschner, Johannes, et autres
Publié: (2024)