Image de couverture de livre

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nanda, Phalguni, Chen, Zaiwei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
par: Nanda, Phalguni, et autres
Publié: (2025)

Recurrent Natural Policy Gradient for POMDPs
par: Cayci, Semih, et autres
Publié: (2024)

From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
par: Chen, Zaiwei, et autres
Publié: (2025)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
par: Ding, Dongsheng, et autres
Publié: (2023)

Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
par: Kong, Deyi, et autres
Publié: (2026)

Achieving $ε^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions
par: Hamza, Ishaq, et autres
Publié: (2026)

Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction
par: Feng, Jie, et autres
Publié: (2024)

A Non-Asymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms
par: Chen, Zaiwei, et autres
Publié: (2025)

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
par: Cayci, Semih, et autres
Publié: (2021)

Demystifying SGD with Doubly Stochastic Gradients
par: Kim, Kyurae, et autres
Publié: (2024)

Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis
par: Liu, Rui, et autres
Publié: (2024)

Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
par: Zeng, Sihan, et autres
Publié: (2024)

From Optimization to Control: Quasi Policy Iteration
par: Kolarijani, Mohammad Amin Sharifi, et autres
Publié: (2023)

Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control
par: Tabas, Sadegh Sadeghi, et autres
Publié: (2024)

Elementary Analysis of Policy Gradient Methods
par: Liu, Jiacai, et autres
Publié: (2024)

On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures
par: Yu, Xian, et autres
Publié: (2023)

Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate
par: Lin, Yifan, et autres
Publié: (2024)

Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators
par: Han, Yinbin, et autres
Publié: (2023)

Concentration of Contractive Stochastic Approximation: Additive and Multiplicative Noise
par: Chen, Zaiwei, et autres
Publié: (2023)

Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization
par: Sun, Youbang, et autres
Publié: (2024)

Delightful Policy Gradient
par: Osband, Ian
Publié: (2026)

Structure Matters: Dynamic Policy Gradient
par: Klein, Sara, et autres
Publié: (2024)

Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
par: Ko, Hojin, et autres
Publié: (2026)

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch
par: Wang, Weizhen, et autres
Publié: (2025)

Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learning
par: Shen, Kaichen, et autres
Publié: (2026)

Delightful Distributed Policy Gradient
par: Osband, Ian
Publié: (2026)

Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator
par: Han, Haoyu, et autres
Publié: (2026)

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
par: Klein, Sara, et autres
Publié: (2023)

Faster Gradient Methods for Highly-Smooth Stochastic Bilevel Optimization
par: Chen, Lesi, et autres
Publié: (2025)

Model-Free Output Feedback Stabilization via Policy Gradient Methods
par: Zhang, Ankang, et autres
Publié: (2026)

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
par: Attia, Amit, et autres
Publié: (2025)

Directional Smoothness and Gradient Methods: Convergence and Adaptivity
par: Mishkin, Aaron, et autres
Publié: (2024)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
par: Semenov, Andrei, et autres
Publié: (2025)

Is Bellman Equation Enough for Learning Control?
par: You, Haoxiang, et autres
Publié: (2025)

Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients
par: Cao, Haoyang, et autres
Publié: (2026)

Policy Gradient with Second Order Momentum
par: Sun, Tianyu
Publié: (2025)

Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
par: Carmona, René, et autres
Publié: (2019)

Policy Gradient Methods for Discrete Time Linear Quadratic Regulator With Random Parameters
par: Li, Deyue
Publié: (2023)

On the Last-Iterate Convergence of Shuffling Gradient Methods
par: Liu, Zijian, et autres
Publié: (2024)

Stochastic Non-Smooth Convex Optimization with Unbounded Gradients
par: Kovalev, Dmitry
Publié: (2026)