paper-with-me

홈 › Papers

Convergence for Natural Policy Gradient on Infinite-State Queueing MDPs

2024-02-07 · Isaac Grosof, Siva Theja Maguluri, R. Srikant

A wide variety of queueing systems can be naturally modeled as infinite-state Markov Decision Processes (MDPs). In the reinforcement learning (RL) context, a variety of algorithms have been developed to learn and optimize these MDPs. At the heart of many popular policy-gradient based learning algorithms, such as natural actor-critic, TRPO, and PPO, lies the Natural Policy Gradient (NPG) policy optimization algorithm. Convergence results for these RL algorithms rest on convergence results for the NPG algorithm. However, all existing results on the convergence of the NPG algorithm are limited to finite-state settings. We study a general class of queueing MDPs, and prove a $O(1/\sqrt{T})$ convergence rate for the NPG algorithm, if the NPG algorithm is initialized with the MaxWeight policy. This is the first convergence rate bound for the NPG algorithm for a general class of infinite-state average-reward MDPs. Moreover, our result applies to a beyond the queueing setting to any countably-infinite MDP satisfying certain mild structural assumptions, given a sufficiently good initial policy. Key to our result are state-dependent bounds on the relative value function achieved by the iterate policies of the NPG algorithm.

📄 PDF Abstract BibTeX arXiv:2402.05274

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…

Similar Papers 제목 키워드 기반

Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes

2020-12-01 · NeurIPS 2020 12 · Dongsheng Ding, Kaiqing Zhang, Tamer Basar, Mihailo Jovanovic

We study sequential decision-making problems in which each agent aims to maximize the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to sol…

Decision MakingSequential Decision Making

On the Convergence Rates of Policy Gradient Methods

2022-01-19 · Lin Xiao

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 me…

Policy Gradient Methods

Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs

2022-06-06 · Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Başar 외

We study sequential decision making problems aimed at maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted…

Decision MakingSequential Decision Making

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

Geometry and convergence of natural policy gradient methods

2022-11-03 · Johannes Müller, Guido Montúfar

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 …

Policy Gradient Methods