Image de couverture de livre

Natural Policy Gradient for Average Reward Non-Stationary RL

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jali, Neharika, Pathak, Eshika, Sharma, Pranay, Qu, Guannan, Joshi, Gauri
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

Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems
par: Jali, Neharika, et autres
Publié: (2024)

Erasure Coded Neural Network Inference via Fisher Averaging
par: Jhunjhunwala, Divyansh, et autres
Publié: (2024)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
par: Jali, Neharika, et autres
Publié: (2026)

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
par: Patel, Shivam, et autres
Publié: (2025)

Improving the Convergence of Private Shuffled Gradient Methods with Public Data
par: Jiang, Shuli, et autres
Publié: (2025)

Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients
par: DeWeese, Alex, et autres
Publié: (2026)

Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning
par: Khodadadian, Sajad, et autres
Publié: (2022)

Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information
par: Zhang, Ziyi, et autres
Publié: (2024)

Initialization Matters: Unraveling the Impact of Pre-Training on Federated Learning
par: Jhunjhunwala, Divyansh, et autres
Publié: (2025)

High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
par: Armacki, Aleksandar, et autres
Publié: (2023)

Sample Complexity of Average-Reward Q-Learning: From Single-agent to Federated Reinforcement Learning
par: Jiao, Yuchen, et autres
Publié: (2026)

Federated Communication-Efficient Multi-Objective Optimization
par: Askin, Baris, et autres
Publié: (2024)

FedAST: Federated Asynchronous Simultaneous Training
par: Askin, Baris, et autres
Publié: (2024)

Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees
par: Armacki, Aleksandar, et autres
Publié: (2024)

Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
par: Ustaomeroglu, Muhammed, et autres
Publié: (2025)

On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes
par: Kumar, Navdeep, et autres
Publié: (2024)

Debiasing Federated Learning with Correlated Client Participation
par: Sun, Zhenyu, et autres
Publié: (2024)

Provable Policy Gradient Methods for Average-Reward Markov Potential Games
par: Cheng, Min, et autres
Publié: (2024)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
par: Askin, Baris, et autres
Publié: (2026)

Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
par: Zurek, Matthew, et autres
Publié: (2025)

Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
par: Ganesh, Swetha, et autres
Publié: (2024)

A Robust Task-Level Control Architecture for Learned Dynamical Systems
par: Pathak, Eshika, et autres
Publié: (2025)

On-Policy RL with Optimal Reward Baseline
par: Hao, Yaru, et autres
Publié: (2025)

Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
par: Wang, Shengbo, et autres
Publié: (2026)

Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
par: Bai, Qinbo, et autres
Publié: (2023)

WARP: On the Benefits of Weight Averaged Rewarded Policies
par: Ramé, Alexandre, et autres
Publié: (2024)

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
par: Woo, Jiin, et autres
Publié: (2024)

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
par: Bai, Qinbo, et autres
Publié: (2024)

Partial Policy Gradients for RL in LLMs
par: Mathur, Puneet, et autres
Publié: (2026)

Average-DICE: Stationary Distribution Correction by Regression
par: Che, Fengdi, et autres
Publié: (2025)

PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
par: Nayak, Anupam, et autres
Publié: (2026)

Functional Natural Policy Gradients
par: Bibaut, Aurelien, et autres
Publié: (2026)

Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL
par: Zurek, Matthew, et autres
Publié: (2025)

Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games
par: Masoumian, Alireza, et autres
Publié: (2024)

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
par: Wen, Xuexiang, et autres
Publié: (2026)

Thinking Beyond Visibility: A Near-Optimal Policy Framework for Locally Interdependent Multi-Agent MDPs
par: DeWeese, Alex, et autres
Publié: (2025)

Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning
par: Xu, Yang, et autres
Publié: (2025)

Lagrangian Index Policy for Restless Bandits with Average Reward
par: Avrachenkov, Konstantin, et autres
Publié: (2024)

Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks
par: Xu, Peiran, et autres
Publié: (2025)

Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
par: He, Xiaoyang, et autres
Publié: (2024)