Copertina

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Yufeng, Chen, Siyu, Yang, Zhuoran, Jordan, Michael I., Wang, Zhaoran
Natura:	Preprint
Pubblicazione:	2021
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory
di: Zhang, Yufeng, et al.
Pubblicazione: (2020)

A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization
di: Zhu, Yuchen, et al.
Pubblicazione: (2024)

Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
di: Yang, Zhuoran, et al.
Pubblicazione: (2020)

Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
di: Cai, Qi, et al.
Pubblicazione: (2022)

Learning Mean-Field Games through Mean-Field Actor-Critic Flow
di: Zhou, Mo, et al.
Pubblicazione: (2025)

Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach
di: Qiu, Shuang, et al.
Pubblicazione: (2022)

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
di: Fouque, Jean-Pierre, et al.
Pubblicazione: (2025)

Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning
di: Li, Zihao, et al.
Pubblicazione: (2024)

Provably Efficient Exploration in Policy Optimization
di: Cai, Qi, et al.
Pubblicazione: (2019)

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
di: He, Jianliang, et al.
Pubblicazione: (2026)

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
di: Kim, Juno, et al.
Pubblicazione: (2023)

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
di: Chen, Siyu, et al.
Pubblicazione: (2024)

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality
di: Chen, Siyu, et al.
Pubblicazione: (2024)

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
di: Bonet, Clément, et al.
Pubblicazione: (2025)

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
di: Altekrüger, Fabian, et al.
Pubblicazione: (2023)

Weak Convergence Analysis of Online Neural Actor-Critic Algorithms
di: Lam, Samuel Chun-Hei, et al.
Pubblicazione: (2024)

On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems
di: Muehlebach, Michael, et al.
Pubblicazione: (2021)

Mirror Mean-Field Langevin Dynamics
di: Gu, Anming, et al.
Pubblicazione: (2025)

Quasi-Newton Compatible Actor-Critic for Deterministic Policies
di: Kordabad, Arash Bahari, et al.
Pubblicazione: (2025)

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
di: Shen, Han, et al.
Pubblicazione: (2024)

A Communication-Efficient Decentralized Actor-Critic Algorithm
di: Ren, Xiaoxing, et al.
Pubblicazione: (2025)

Muon Dynamics as a Spectral Wasserstein Flow
di: Peyré, Gabriel
Pubblicazione: (2026)

Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
di: Zeng, Sihan, et al.
Pubblicazione: (2024)

Achieving $ε^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions
di: Hamza, Ishaq, et al.
Pubblicazione: (2026)

High-dimensional Mean-Field Games by Particle-based Flow Matching
di: Yu, Jiajia, et al.
Pubblicazione: (2025)

Wasserstein Distributionally Robust Online Learning
di: Chen, Guixian, et al.
Pubblicazione: (2026)

A Computational Framework for Solving Wasserstein Lagrangian Flows
di: Neklyudov, Kirill, et al.
Pubblicazione: (2023)

An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints
di: Lekeufack, Jordan, et al.
Pubblicazione: (2024)

CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization
di: Alboni, Elisa, et al.
Pubblicazione: (2023)

The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
di: Muehlebach, Michael, et al.
Pubblicazione: (2025)

A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
di: Zeng, Sihan, et al.
Pubblicazione: (2026)

Learning to Stop: Deep Learning for Mean Field Optimal Stopping
di: Magnino, Lorenzo, et al.
Pubblicazione: (2024)

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity
di: Zhu, Shuailong, et al.
Pubblicazione: (2025)

Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
di: Chemseddine, Jannis, et al.
Pubblicazione: (2024)

Enhancing Distributional Robustness in Principal Component Analysis by Wasserstein Distances
di: Wang, Lei, et al.
Pubblicazione: (2025)

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
di: Yang, Tong, et al.
Pubblicazione: (2025)

ACING: Actor-Critic for Instruction Learning in Black-Box LLMs
di: Kharrat, Salma, et al.
Pubblicazione: (2024)

Mean-Field Generalisation Bounds for Learning Controls in Stochastic Environments
di: Baros, Boris, et al.
Pubblicazione: (2025)

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
di: Wang, Guillaume, et al.
Pubblicazione: (2024)

Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
di: Ren, Yinuo, et al.
Pubblicazione: (2023)