paper-with-me

Papers

Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization

2022-09-30 · Carlo Alfano, Patrick Rebeschini

We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes. In the deterministic case, when the Q-value is known and can be approximated by a linear combination of a known feature function up to a bias error, we show that a geometrically-increasing step size yields a linear convergence rate towards an optimal policy. We then consider the sample-based case, when the best representation of the Q- value function among linear combinations of a known feature function is known up to an estimation error. In this setting, we show that the algorithm enjoys the same linear guarantees as in the deterministic case up to an error term that depends on the estimation error, the bias error, and the condition number of the feature covariance matrix. Our results build upon the general framework of policy mirror descent and extend previous findings for the softmax tabular parametrization to the log-linear policy class.

📄 PDF Abstract BibTeX arXiv:2209.15382

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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

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…

Policy Gradient Methods

Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients

2024-03-28 · Johannes Müller, Semih Çaycı, Guido Montúfar

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information m…

On the Linear convergence of Natural Policy Gradient Algorithm

2021-05-04 · Sajad Khodadadian, Prakirt Raj Jhunjhunwala, Sushil Mahavir Varma, Siva Theja Maguluri

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 gradi…

Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies

2022-10-04 · Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric 외

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…

Policy Gradient Methods

Quasi-Newton Iteration in Deterministic Policy Gradient

2022-03-25 · Arash Bahari Kordabad, Hossein Nejatbakhsh Esfahani, WenQi Cai, Sebastien Gros

This paper presents a model-free approximation for the Hessian of the performance of deterministic policies to use in the context of Reinforcement Learning based on Quasi-Newton steps in the policy parameters. We show th…

reinforcement-learningReinforcement Learning (RL)