English
Related papers

Related papers: Towards Principled, Practical Policy Gradient for …

200 papers

Policy gradient (PG) methods are popular and efficient for large-scale reinforcement learning due to their relative stability and incremental nature. In recent years, the empirical success of PG methods has led to the development of a…

Machine Learning · Computer Science 2022-05-24 Yuhao Ding , Junzi Zhang , Javad Lavaei

We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an $O(1/t)$ rate, even with a \emph{constant} step size. Remarkably, global convergence of the stochastic gradient bandit…

Machine Learning · Computer Science 2024-02-28 Jincheng Mei , Zixin Zhong , Bo Dai , Alekh Agarwal , Csaba Szepesvari , Dale Schuurmans

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human…

Machine Learning · Computer Science 2021-06-23 Zaynah Javed , Daniel S. Brown , Satvik Sharma , Jerry Zhu , Ashwin Balakrishna , Marek Petrik , Anca D. Dragan , Ken Goldberg

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

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\mathcal{P}$ using samples from…

Machine Learning · Computer Science 2020-06-11 Craig Boutilier , Chih-Wei Hsu , Branislav Kveton , Martin Mladenov , Csaba Szepesvari , Manzil Zaheer

We consider a setting involving $N$ agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents' MDPs differ in their reward functions, capturing heterogeneous objectives/tasks. The…

Machine Learning · Computer Science 2024-09-10 Feng Zhu , Robert W. Heath , Aritra Mitra

Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient methods in reinforcement learning (RL). However, the theoretical understanding of…

Machine Learning · Computer Science 2024-07-16 Yuhao Ding , Junzi Zhang , Hyunin Lee , Javad Lavaei

We study a finite time horizon Markov decision process (MDP) consisting of several groups of multi-action finite-state restless bandit processes, which are identical within each group. The bandit processes into different groups can be…

Optimization and Control · Mathematics 2026-04-20 Jing Fu , Bill Moran , Jose Nino-Mora

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods…

Machine Learning · Computer Science 2018-06-15 Matteo Papini , Damiano Binaghi , Giuseppe Canonaco , Matteo Pirotta , Marcello Restelli

Motivated by penalized likelihood maximization in complex models, we study optimization problems where neither the function to optimize nor its gradient have an explicit expression, but its gradient can be approximated by a Monte Carlo…

Computation · Statistics 2017-09-28 Gersende Fort , Edouard Ollier , Adeline Samson

Policy gradient (PG) estimators are ineffective in dealing with softmax policies that are sub-optimally saturated, which refers to the situation when the policy concentrates its probability mass on sub-optimal actions. Sub-optimal policy…

Machine Learning · Computer Science 2022-02-25 Shivam Garg , Samuele Tosatto , Yangchen Pan , Martha White , A. Rupam Mahmood

A novel Policy Gradient (PG) algorithm, called $\textit{Matryoshka Policy Gradient}$ (MPG), is introduced and studied, in the context of fixed-horizon max-entropy reinforcement learning, where an agent aims at maximizing entropy bonuses…

Machine Learning · Computer Science 2024-10-10 François Ged , Maria Han Veiga

Policy gradient (PG) is a reinforcement learning (RL) approach that optimizes a parameterized policy model for an expected return using gradient ascent. While PG can work well even in non-Markovian environments, it may encounter plateaus or…

Machine Learning · Computer Science 2024-07-08 Tetsuro Morimura , Kazuhiro Ota , Kenshi Abe , Peinan Zhang

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

This brief paper presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for…

Optimization and Control · Mathematics 2014-12-17 Hyeong Soo Chang

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central…

Optimization and Control · Mathematics 2022-11-01 Runyu Zhang , Jincheng Mei , Bo Dai , Dale Schuurmans , Na Li

This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan