English
Related papers

Related papers: On the Global Convergence Rates of Softmax Policy …

200 papers

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function…

Machine Learning · Computer Science 2026-05-26 Ziyue Chen , David Šiška , Lukasz Szpruch

Policy gradient methods are known to be highly sensitive to the choice of policy parameterization. In particular, the widely used softmax parameterization can induce ill-conditioned optimization landscapes and lead to exponentially slow…

Machine Learning · Computer Science 2026-04-02 Safwan Labbi , Daniil Tiapkin , Paul Mangold , Eric Moulines

We provide global convergence rates for vanilla and entropy-regularized federated softmax stochastic policy gradient (FedPG) with local training. We show that FedPG converges to a near-optimal policy in terms of the average agent value,…

Machine Learning · Computer Science 2026-04-02 Safwan Labbi , Paul Mangold , Daniil Tiapkin , Eric Moulines

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…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

We study the global convergence of policy gradient for infinite-horizon, continuous state and action space, and entropy-regularized Markov decision processes (MDPs). We consider a softmax policy with (one-hidden layer) neural network…

Optimization and Control · Mathematics 2022-06-17 Bekzhan Kerimkulov , James-Michael Leahy , David Šiška , Lukasz Szpruch

Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient methods in reinforcement learning (RL). However, the theoretical understanding of…

Machine Learning · Computer Science 2024-07-16 Yuhao Ding , Junzi Zhang , Hyunin Lee , Javad Lavaei

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted…

Machine Learning · Computer Science 2022-12-19 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy…

Machine Learning · Computer Science 2026-02-17 Semih Cayci , Niao He , R. Srikant

Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a…

Optimization and Control · Mathematics 2024-06-04 Wouter Jongeneel , Daniel Kuhn , Mengmeng Li

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic…

Machine Learning · Computer Science 2022-06-22 Jalaj Bhandari , Daniel Russo

A novel Policy Gradient (PG) algorithm, called $\textit{Matryoshka Policy Gradient}$ (MPG), is introduced and studied, in the context of fixed-horizon max-entropy reinforcement learning, where an agent aims at maximizing entropy bonuses…

Machine Learning · Computer Science 2024-10-10 François Ged , Maria Han Veiga

We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength, both in a weighted…

Optimization and Control · Mathematics 2025-12-16 Johannes Müller , Semih Cayci

Entropy regularization has been widely used in policy optimization algorithms to enhance exploration and the robustness of the optimal control; however it also introduces an additional regularization bias. This work quantifies the impact of…

Optimization and Control · Mathematics 2025-03-25 Deven Sethi , David Šiška , Yufei Zhang

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-intuitive, impractical and often opaque conditions. In…

Machine Learning · Computer Science 2022-04-08 Matthew S. Zhang , Murat A. Erdogdu , Animesh Garg

In this paper, we establish the global optimality and convergence rate of an off-policy actor critic algorithm in the tabular setting without using density ratio to correct the discrepancy between the state distribution of the behavior…

Machine Learning · Computer Science 2025-02-07 Shangtong Zhang , Remi Tachet , Romain Laroche

In reinforcement learning, the softmax parametrization is the standard approach for policies over discrete action spaces. However, it fails to capture the order relationship between actions. Motivated by a real-world industrial problem, we…

Machine Learning · Computer Science 2025-06-24 Simón Weinberger , Jairo Cugliari

We consider infinite-horizon discounted Markov decision problems with finite state and action spaces and study the convergence rates of the projected policy gradient method and a general class of policy mirror descent methods, all with…

Optimization and Control · Mathematics 2022-03-08 Lin Xiao
‹ Prev 1 2 3 10 Next ›