Copertina

Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lu, Michael, Aghaei, Matin, Raj, Anant, Vaswani, Sharan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From Inverse Optimization to Feasibility to ERM
di: Mishra, Saurabh, et al.
Pubblicazione: (2024)

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

Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
di: Lu, Michael, et al.
Pubblicazione: (2026)

Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
di: Liu, Xingtu, et al.
Pubblicazione: (2025)

Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
di: Vaswani, Sharan, et al.
Pubblicazione: (2025)

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
di: Vaswani, Sharan, et al.
Pubblicazione: (2021)

Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
di: Asad, Reza, et al.
Pubblicazione: (2025)

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

Towards Optimal Differentially Private Regret Bounds in Linear MDPs
di: Sahu, Sharan
Pubblicazione: (2025)

Towards Parameter-Free Temporal Difference Learning
di: Li, Yunxiang, et al.
Pubblicazione: (2026)

Towards Provable Log Density Policy Gradient
di: Katdare, Pulkit, et al.
Pubblicazione: (2024)

(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum
di: Dang, Anh, et al.
Pubblicazione: (2024)

Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
di: Vaswani, Sharan, et al.
Pubblicazione: (2026)

On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
di: Shah, Anvay, et al.
Pubblicazione: (2026)

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

Fast Convergence of Softmax Policy Mirror Ascent
di: Asad, Reza, et al.
Pubblicazione: (2024)

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

Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
di: Zhang, Runyu, et al.
Pubblicazione: (2023)

Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
di: Lin, Jiabin, et al.
Pubblicazione: (2024)

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
di: Lancewicki, Tal, et al.
Pubblicazione: (2025)

Glocal Smoothness: Line search and adaptive step sizes can help in theory too!
di: Fox, Curtis, et al.
Pubblicazione: (2025)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
di: Tsuchiya, Taira, et al.
Pubblicazione: (2025)

Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs
di: Lee, Jongmin, et al.
Pubblicazione: (2025)

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
di: Li, Mingyi, et al.
Pubblicazione: (2026)

Convergence of Natural Policy Gradient for a Family of Infinite-State Queueing MDPs
di: Grosof, Isaac, et al.
Pubblicazione: (2024)

Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
di: Peng, Shuman, et al.
Pubblicazione: (2024)

TabKAN: Advancing Tabular Data Analysis using Kolmogorov-Arnold Network
di: Eslamian, Ali, et al.
Pubblicazione: (2025)

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
di: Cassel, Asaf, et al.
Pubblicazione: (2024)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
di: Kash, Ian A., et al.
Pubblicazione: (2022)

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs
di: Wang, Jing, et al.
Pubblicazione: (2026)

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
di: Kitamura, Toshinori, et al.
Pubblicazione: (2024)

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

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
di: Chen, Shulun, et al.
Pubblicazione: (2025)

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
di: Liu, Haolin, et al.
Pubblicazione: (2024)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
di: Ito, Shinji, et al.
Pubblicazione: (2025)

Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
di: Ganesh, Swetha, et al.
Pubblicazione: (2024)

A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits
di: Lattimore, Tor
Pubblicazione: (2026)

Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
di: Kale, Sacchit, et al.
Pubblicazione: (2026)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
di: Li, Long-Fei, et al.
Pubblicazione: (2024)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
di: Ding, Dongsheng, et al.
Pubblicazione: (2023)