English
Related papers

Related papers: Natural Policy Gradient as Doubly Smoothed Policy …

200 papers

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

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…

Machine Learning · Computer Science 2025-07-14 Isaac Grosof , Siva Theja Maguluri , R. Srikant

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies. An online variant…

Machine Learning · Computer Science 2019-04-09 Nikolaos Tziortziotis , Christos Dimitrakakis , Michalis Vazirgiannis

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

Machine Learning · Computer Science 2016-07-18 William Montgomery , Sergey Levine

Decision-making problems in uncertain or stochastic domains are often formulated as Markov decision processes (MDPs). Policy iteration (PI) is a popular algorithm for searching over policy-space, the size of which is exponential in the…

Artificial Intelligence · Computer Science 2013-01-30 Yishay Mansour , Satinder Singh

We cast Amari's natural gradient in statistical learning as a specific case of Kalman filtering. Namely, applying an extended Kalman filter to estimate a fixed unknown parameter of a probabilistic model from a series of observations, is…

Machine Learning · Statistics 2018-08-29 Yann Ollivier

Policy Iteration (PI) is a classical family of algorithms to compute an optimal policy for any given Markov Decision Problem (MDP). The basic idea in PI is to begin with some initial policy and to repeatedly update the policy to one from an…

In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a policy that optimizes a linear function of its state-action…

Machine Learning · Computer Science 2023-08-30 Navdeep Kumar , Kaixin Wang , Kfir Levy , Shie Mannor

The training of machine learning models is typically carried out using some form of gradient descent, often with great success. However, non-asymptotic analyses of first-order optimization algorithms typically employ a gradient smoothness…

Machine Learning · Computer Science 2024-06-18 Thomas Flynn

Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in general online settings, when combined with world model and…

Machine Learning · Computer Science 2026-01-29 Florent Delgrange , Raphael Avalos , Willem Röpke

Importance sampling (IS) represents a fundamental technique for a large surge of off-policy reinforcement learning approaches. Policy gradient (PG) methods, in particular, significantly benefit from IS, enabling the effective reuse of…

Machine Learning · Computer Science 2024-05-10 Matteo Papini , Giorgio Manganini , Alberto Maria Metelli , Marcello Restelli

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Although average gain optimality is a commonly adopted performance measure in Markov Decision Processes (MDPs), it is often too asymptotic. Further incorporating measures of immediate losses leads to the hierarchy of bias optimalities, all…

Machine Learning · Computer Science 2025-10-16 Victor Boone , Adrienne Tuynman

Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \texttt{sa}-rectangular robust MDPs exist, using its…

Artificial Intelligence · Computer Science 2022-10-06 Navdeep Kumar , Kfir Levy , Kaixin Wang , Shie Mannor

The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existing exploration methods are mostly based on adding noise to…

Machine Learning · Computer Science 2018-03-28 Tianbing Xu , Qiang Liu , Liang Zhao , Jian Peng

Policy Iteration (PI) is a widely used family of algorithms to compute optimal policies for Markov Decision Problems (MDPs). We derive upper bounds on the running time of PI on Deterministic MDPs (DMDPs): the class of MDPs in which every…

Discrete Mathematics · Computer Science 2023-10-10 Ritesh Goenka , Eashan Gupta , Sushil Khyalia , Pratyush Agarwal , Mulinti Shaik Wajid , Shivaram Kalyanakrishnan

A dynamic mean field theory is developed for finite state and action Bayesian reinforcement learning in the large state space limit. In an analogy with statistical physics, the Bellman equation is studied as a disordered dynamical system;…

Machine Learning · Statistics 2023-07-13 George Stamatescu
‹ Prev 1 4 5 6 7 8 10 Next ›