English
Related papers

Related papers: Ordering-based Conditions for Global Convergence o…

200 papers

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

We consider infinite-horizon discounted Markov decision processes and study the convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log-linear policy class. Using the compatible function approximation…

Machine Learning · Computer Science 2023-02-22 Rui Yuan , Simon S. Du , Robert M. Gower , Alessandro Lazaric , Lin Xiao

We make three contributions toward better understanding policy gradient methods in the tabular setting. First, we show that with the true gradient, policy gradient with a softmax parametrization converges at a $O(1/t)$ rate, with constants…

Machine Learning · Computer Science 2022-06-03 Jincheng Mei , Chenjun Xiao , Csaba Szepesvari , Dale Schuurmans

Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neural" policy gradient…

Machine Learning · Computer Science 2020-06-23 Lingxiao Wang , Qi Cai , Zhuoran Yang , Zhaoran Wang

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

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

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes…

Optimization and Control · Mathematics 2024-09-19 Jiacai Liu , Wenye Li , Dachao Lin , Ke Wei , Zhihua Zhang

Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that corresponds to mirror ascent…

Machine Learning · Computer Science 2025-06-02 Reza Asad , Reza Babanezhad , Issam Laradji , Nicolas Le Roux , Sharan Vaswani

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We study the convergence of several natural policy gradient (NPG) methods in infinite-horizon discounted Markov decision processes with regular policy parametrizations. For a variety of NPGs and reward functions we show that the…

Optimization and Control · Mathematics 2024-02-21 Johannes Müller , Guido Montúfar

Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning. Inspired by prior work, a new NPG variant coined NPG-HM is developed in this paper, which utilizes the Hessian-aided momentum…

Machine Learning · Computer Science 2024-01-23 Jie Feng , Ke Wei , Jinchi Chen

Policy gradient (PG) estimation becomes a challenge when we are not allowed to sample with the target policy but only have access to a dataset generated by some unknown behavior policy. Conventional methods for off-policy PG estimation…

Machine Learning · Statistics 2022-06-22 Chengzhuo Ni , Ruiqi Zhang , Xiang Ji , Xuezhou Zhang , Mengdi Wang

While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to…

Optimization and Control · Mathematics 2023-04-25 Feiran Zhao , Xingyun Fu , Keyou You

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…

Machine Learning · Computer Science 2023-10-11 Siddhant Agarwal , Ishan Durugkar , Peter Stone , Amy Zhang

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

Machine Learning · Computer Science 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

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

Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes and ensuring reliable performance in highly stochastic sequential decision-making problems. While it has been shown that…

Machine Learning · Computer Science 2026-01-21 Xian Yu , Lei Ying