paper-with-me

Papers

Elementary Analysis of Policy Gradient Methods

2024-04-04 · Jiacai Liu, Wenye Li, Ke Wei

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent activities in studying these algorithms from the theoretical aspect. Despite this, their convergence behavior is still not fully understood, even given the access to exact policy evaluations. In this paper, we focus on the discounted MDP setting and conduct a systematic study of the aforementioned policy optimization methods. Several novel results are presented, including 1) global linear convergence of projected policy gradient for any constant step size, 2) sublinear convergence of softmax policy gradient for any constant step size, 3) global linear convergence of softmax natural policy gradient for any constant step size, 4) global linear convergence of entropy regularized softmax policy gradient for a wider range of constant step sizes than existing result, 5) tight local linear convergence rate of entropy regularized natural policy gradient, and 6) a new and concise local quadratic convergence rate of soft policy iteration without the assumption on the stationary distribution under the optimal policy. New and elementary analysis techniques have been developed to establish these results.

📄 PDF Abstract BibTeX arXiv:2404.03372

Code (0)

등록된 구현이 없습니다.

Tasks

Policy Gradient Methods

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Gradient Descent-Type Methods: Background and Simple Unified Convergence Analysis

2022-12-19 · Quoc Tran-Dinh, Marten van Dijk

In this book chapter, we briefly describe the main components that constitute the gradient descent method and its accelerated and stochastic variants. We aim at explaining these components from a mathematical point of vi…

Vocal Bursts Type Prediction

Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^{-7/4})$ Complexity

2022-01-27 · Huan Li, Zhouchen Lin

This paper studies accelerated gradient methods for nonconvex optimization with Lipschitz continuous gradient and Hessian. We propose two simple accelerated gradient methods, restarted accelerated gradient descent (AGD) …

Weighted Quantum Channel Compiling through Proximal Policy Optimization

2021-11-03 · Weiyuan Gong, Si Jiang, Dong-Ling Deng

We propose a general and systematic strategy to compile arbitrary quantum channels without using ancillary qubits, based on proximal policy optimization -- a powerful deep reinforcement learning algorithm. We rigorously …

Deep Reinforcement Learning

Backstepping Temporal Difference Learning

2023-02-20 · Han-Dong Lim, Donghwan Lee

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer…

Reinforcement Learning (RL)

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

2025-03-28 · Weizhen Wang, Jianping He, Xiaoming Duan

Policy gradient methods are one of the most successful methods for solving challenging reinforcement learning problems. However, despite their empirical successes, many SOTA policy gradient algorithms for discounted prob…

Policy Gradient Methods