English
Related papers

Related papers: On Policy Gradients

200 papers

Gradient descent is the method of choice for training large artificial intelligence systems. As these systems become larger, a better understanding of the mechanisms behind gradient training would allow us to alleviate compute costs and…

Machine Learning · Computer Science 2025-01-07 Ambroise Odonnat , Wassim Bouaziz , Vivien Cabannes

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Machine Learning · Computer Science 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they are either…

Machine Learning · Computer Science 2023-12-05 Qinghua Liu , Gellért Weisz , András György , Chi Jin , Csaba Szepesvári

Policy gradient methods are notorious for having a large variance and high sample complexity. To mitigate this, we introduce SoftTreeMax -- a generalization of softmax that employs planning. In SoftTreeMax, we extend the traditional logits…

Machine Learning · Computer Science 2025-05-27 Gal Dalal , Assaf Hallak , Gugan Thoppe , Shie Mannor , Gal Chechik

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance.…

Machine Learning · Statistics 2017-09-18 Yingfei Wang , Chu Wang , Warren Powell

In practice, optimization tasks have some structure that allows developing new algorithms for every problem with faster convergence rates. Using the structure of optimization tasks, we can propose algorithms with more optimistic convergence…

Optimization and Control · Mathematics 2020-09-01 Alexander Tyurin

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by…

Machine Learning · Computer Science 2017-12-07 Peter Henderson , Thang Doan , Riashat Islam , David Meger

Gradient Descent (GD) is a ubiquitous algorithm for finding the optimal solution to an optimization problem. For reduced computational complexity, the optimal solution $\mathrm{x^*}$ of the optimization problem must be attained in a minimum…

Optimization and Control · Mathematics 2023-06-01 Revati Gunjal , Sushama Wagh , Syed Shadab Nayyer , Alex Stankovic , Navdeep M. Singh

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

This paper investigates the privacy-preserving distributed optimization problem, aiming to protect agents' private information from potential attackers during the optimization process. Gradient tracking, an advanced technique for improving…

Machine Learning · Computer Science 2025-09-24 Furan Xie , Bing Liu , Li Chai

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.…

Machine Learning · Computer Science 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

We study the risk-sensitive exponential cost MDP formulation and develop a trajectory-based gradient algorithm to find the stationary point of the cost associated with a set of parameterized policies. We derive a formula that can be used to…

Systems and Control · Electrical Eng. & Systems 2022-08-31 Mehrdad Moharrami , Yashaswini Murthy , Arghyadip Roy , R. Srikant

We develop an optimization framework centered around a core idea: once a (parametric) policy is specified, control authority is transferred to the policy, resulting in an autonomous dynamical system. Thus we should be able to optimize…

Machine Learning · Computer Science 2025-06-11 Emo Todorov

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov

This paper is a broad and accessible survey of the methods we have at our disposal for Monte Carlo gradient estimation in machine learning and across the statistical sciences: the problem of computing the gradient of an expectation of a…

Machine Learning · Statistics 2020-09-30 Shakir Mohamed , Mihaela Rosca , Michael Figurnov , Andriy Mnih

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each change of the target policy, its value is estimated from the…

Artificial Intelligence · Computer Science 2007-05-23 Leonid Peshkin , Christian R. Shelton

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

Machine Learning · Computer Science 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is a special case within the general family of automatic…

Machine Learning · Computer Science 2022-02-18 Atılım Güneş Baydin , Barak A. Pearlmutter , Don Syme , Frank Wood , Philip Torr