Cover Image

Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Jongmin, Ryu, Ernest K.
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

Policy Gradient Algorithms in Average-Reward Multichain MDPs
by: Lee, Jongmin, et al.
Published: (2026)

Finite-Time Bounds for Average-Reward Fitted Q-Iteration
by: Lee, Jongmin, et al.
Published: (2025)

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
by: Bai, Qinbo, et al.
Published: (2024)

Deflated Dynamics Value Iteration
by: Lee, Jongmin, et al.
Published: (2024)

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

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
by: Hong, Kihyuk, et al.
Published: (2024)

Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes
by: Lee, Jongmin, et al.
Published: (2025)

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

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

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

Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
by: Lu, Michael, et al.
Published: (2024)

Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
by: Nie, Wenhua, et al.
Published: (2026)

Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
by: Li, Mengmeng, et al.
Published: (2023)

Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization
by: Satheesh, Anirudh, et al.
Published: (2026)

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

Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
by: Wang, Shengbo, et al.
Published: (2026)

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
by: Hong, Kihyuk, et al.
Published: (2025)

ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
by: Agnihotri, Akhil, et al.
Published: (2023)

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

Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm
by: Xu, Yang, et al.
Published: (2025)

Gradient-free Decoder Inversion in Latent Diffusion Models
by: Hong, Seongmin, et al.
Published: (2024)

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span
by: Chae, Woojin, et al.
Published: (2024)

When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
by: Escamilla, Jose Efraim Aguilar, et al.
Published: (2026)

Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
by: Shakerinava, Mehran, et al.
Published: (2025)

ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control
by: Futuhi, Ehsan, et al.
Published: (2024)

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

Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
by: Wei, Yukuan, et al.
Published: (2025)

Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
by: Satheesh, Anirudh, et al.
Published: (2026)

Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation
by: Panda, Prashansa, et al.
Published: (2024)

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
by: Gadot, Uri, et al.
Published: (2023)

LoRA Training in the NTK Regime has No Spurious Local Minima
by: Jang, Uijeong, et al.
Published: (2024)

Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
by: Bai, Qinbo, et al.
Published: (2023)

LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)
by: Kim, Junsu, et al.
Published: (2025)

Natural Policy Gradient for Average Reward Non-Stationary RL
by: Jali, Neharika, et al.
Published: (2025)

Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
by: Ganesh, Swetha, et al.
Published: (2025)

Residual Policy Gradient: A Reward View of KL-regularized Objective
by: Wang, Pengcheng, et al.
Published: (2025)

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
by: Zhang, Junkai, et al.
Published: (2023)

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

Difference Rewards Policy Gradients
by: Castellini, Jacopo, et al.
Published: (2020)

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