English
Related papers

Related papers: Natural Option Critic

200 papers

Optimizing dynamic risk with stochastic policies is challenging in both policy updates and value learning. The former typically requires transition perturbation, while the latter may rely on model-based approaches. To address these…

Machine Learning · Computer Science 2026-05-11 Yudong Luo , Erick Delage

In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian…

Machine Learning · Computer Science 2026-04-02 Deyi Kong , Zaiwei Chen , Shuzhong Zhang , Shancong Mou

Reinforcement learning has proven its power on various occasions. However, its performance is not always guaranteed when system dynamics change. Instead, it largely relies on users' empirical experience. For reinforcement learning…

Machine Learning · Computer Science 2026-05-05 Jingyi Liu , Jian Guo , Eberhard Gill

Actor-critic style two-time-scale algorithms are one of the most popular methods in reinforcement learning, and have seen great empirical success. However, their performance is not completely understood theoretically. In this paper, we…

Machine Learning · Computer Science 2022-02-22 Sajad Khodadadian , Thinh T. Doan , Justin Romberg , Siva Theja Maguluri

Estimating and quantifying uncertainty in unknown system parameters from limited data remains a challenging inverse problem in a variety of real-world applications. While many approaches focus on estimating constant parameters, a subset of…

Methodology · Statistics 2023-05-09 Andrea Arnold

We extend the standard reinforcement learning framework to random time horizons. While the classical setting typically assumes finite and deterministic or infinite runtimes of trajectories, we argue that multiple real-world applications…

Machine Learning · Computer Science 2025-08-15 Enric Ribera Borrell , Lorenz Richter , Christof Schütte

We propose a new way of deriving policy gradient updates for reinforcement learning. Our technique, based on Fourier analysis, recasts integrals that arise with expected policy gradients as convolutions and turns them into multiplications.…

Machine Learning · Computer Science 2018-05-31 Matthew Fellows , Kamil Ciosek , Shimon Whiteson

We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths. The resulting natural path gradient performs policy updates in a…

Machine Learning · Computer Science 2020-01-03 Daniel McNamee

Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal…

Machine Learning · Computer Science 2025-04-11 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

Natural gradient methods have been used to optimise the parameters of probability distributions in a variety of settings, often resulting in fast-converging procedures. Unfortunately, for many distributions of interest, computing the…

Machine Learning · Statistics 2024-05-28 Jonathan So , Richard E. Turner

The natural gradient method is widely used in statistical optimization, but its standard formulation assumes a Euclidean parameter space. This paper proposes an inversion-free stochastic natural gradient method for probability distributions…

Machine Learning · Statistics 2026-04-06 Dario Draca , Takuo Matsubara , Minh-Ngoc Tran

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Machine Learning · Computer Science 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

The most relevant problems in discounted reinforcement learning involve estimating the mean of a function under the stationary distribution of a Markov reward process, such as the expected return in policy evaluation, or the policy gradient…

Machine Learning · Computer Science 2023-04-17 Alberto Maria Metelli , Mirco Mutti , Marcello Restelli

Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…

Machine Learning · Computer Science 2019-06-21 Ehsan Imani , Eric Graves , Martha White

In Reinforcement Learning, the optimal action at a given state is dependent on policy decisions at subsequent states. As a consequence, the learning targets evolve with time and the policy optimization process must be efficient at…

Machine Learning · Computer Science 2022-02-16 Romain Laroche , Remi Tachet

We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-03-10 Anirudh Satheesh , Pankaj Kumar Barman , Washim Uddin Mondal , Vaneet Aggarwal

Reinforcement learning is a growing field in AI with a lot of potential. Intelligent behavior is learned automatically through trial and error in interaction with the environment. However, this learning process is often costly. Using…

Quantum Physics · Physics 2023-12-08 Nico Meyer , Daniel D. Scherer , Axel Plinge , Christopher Mutschler , Michael J. Hartmann

We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent direction that is motivated by the solution of a certain non-linear…

Machine Learning · Computer Science 2015-07-30 Prashanth L. A. , H. L. Prasad , Shalabh Bhatnagar , Prakash Chandra

The idea that the brain functions so as to minimize certain costs pervades theoretical neuroscience. Since a cost function by itself does not predict how the brain finds its minima, additional assumptions about the optimization method need…

Neurons and Cognition · Quantitative Biology 2018-12-24 Simone Carlo Surace , Jean-Pascal Pfister , Wulfram Gerstner , Johanni Brea