Cover Image

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mei, Jincheng, Dai, Bo, Agarwal, Alekh, Ghavamzadeh, Mohammad, Szepesvari, Csaba, Schuurmans, Dale
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stochastic Gradient Succeeds for Bandits
by: Mei, Jincheng, et al.
Published: (2024)

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
by: Lin, Max Qiushi, et al.
Published: (2025)

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
by: Mei, Jincheng, et al.
Published: (2025)

Rectifying Regression in Reinforcement Learning
by: Ayoub, Alex, et al.
Published: (2025)

Learning to Reason Efficiently with Discounted Reinforcement Learning
by: Ayoub, Alex, et al.
Published: (2025)

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs
by: Tian, Tian, et al.
Published: (2024)

Beyond Expectations: Learning with Stochastic Dominance Made Practical
by: Cen, Shicong, et al.
Published: (2024)

Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning
by: Dai, Bo, et al.
Published: (2026)

Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment
by: Yang, Tong, et al.
Published: (2024)

Sharper Guarantees for Misspecified Kernelized Bandit Optimization
by: Maran, Davide, et al.
Published: (2026)

Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling
by: Agarwal, Alekh, et al.
Published: (2022)

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

Sharp analysis of linear ensemble sampling
by: Akhavan, Arya, et al.
Published: (2026)

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
by: Cen, Shicong, et al.
Published: (2024)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
by: Zhong, Han, et al.
Published: (2021)

Spectral Representation-based Reinforcement Learning
by: Gao, Chenxiao, et al.
Published: (2025)

Balancing optimism and pessimism in offline-to-online learning
by: Sentenac, Flore, et al.
Published: (2025)

On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures
by: Yu, Xian, et al.
Published: (2023)

Ensemble sampling for linear bandits: small ensembles suffice
by: Janz, David, et al.
Published: (2023)

Mitigating Preference Hacking in Policy Optimization with Pessimism
by: Gupta, Dhawal, et al.
Published: (2025)

Exploration via linearly perturbed loss minimisation
by: Janz, David, et al.
Published: (2023)

Delightful Gradients Accelerate Corner Escape
by: Mei, Jincheng, et al.
Published: (2026)

Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
by: Lin, Max Qiushi, et al.
Published: (2026)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
by: Ganesh, Swetha, et al.
Published: (2024)

Design Considerations in Offline Preference-based RL
by: Agarwal, Alekh, et al.
Published: (2025)

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
by: Zhang, Hongming, et al.
Published: (2023)

Policy Gradient in Robust MDPs with Global Convergence Guarantee
by: Wang, Qiuhao, et al.
Published: (2022)

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
by: Che, Fengdi, et al.
Published: (2024)

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
by: György, András, et al.
Published: (2025)

Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis
by: Hau, Jia Lin, et al.
Published: (2024)

Eluder dimension: localise it!
by: Bakhtiari, Alireza, et al.
Published: (2026)

Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits
by: Liu, Shuai, et al.
Published: (2026)

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
by: Liu, Shuai, et al.
Published: (2024)

Stochastic Gradient Descent for Gaussian Processes Done Right
by: Lin, Jihao Andreas, et al.
Published: (2023)

Bayesian Regret Minimization in Offline Bandits
by: Petrik, Marek, et al.
Published: (2023)

Bayesian policy gradient and actor-critic algorithms
by: Ghavamzadeh, Mohammad, et al.
Published: (2026)

Contextual Bandits with Stage-wise Constraints
by: Pacchiano, Aldo, et al.
Published: (2024)

Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
by: Zhu, Zhaoyu, et al.
Published: (2026)

Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
by: Montenegro, Alessandro, et al.
Published: (2024)

Plastic Learning with Deep Fourier Features
by: Lewandowski, Alex, et al.
Published: (2024)