English
Related papers

Related papers: Correcting discount-factor mismatch in on-policy p…

200 papers

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to study each effect in isolation. Our analysis reveals that the…

Machine Learning · Computer Science 2019-12-24 Harm van Seijen , Mehdi Fatemi , Arash Tavakoli

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

Distribution-based search algorithms are an effective approach for evolutionary reinforcement learning of neural network controllers. In these algorithms, gradients of the total reward with respect to the policy parameters are estimated…

Neural and Evolutionary Computing · Computer Science 2020-12-09 Nihat Engin Toklu , Paweł Liskowski , Rupesh Kumar Srivastava

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any…

Optimization and Control · Mathematics 2019-06-07 Aaron Sidford , Mengdi Wang , Xian Wu , Lin F. Yang , Yinyu Ye

Policy gradient methods are notorious for having a large variance and high sample complexity. To mitigate this, we introduce SoftTreeMax -- a generalization of softmax that employs planning. In SoftTreeMax, we extend the traditional logits…

Machine Learning · Computer Science 2025-05-27 Gal Dalal , Assaf Hallak , Gugan Thoppe , Shie Mannor , Gal Chechik

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by…

Machine Learning · Computer Science 2017-12-07 Peter Henderson , Thang Doan , Riashat Islam , David Meger

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite…

Machine Learning · Computer Science 2019-10-14 Xinyun Chen , Lu Wang , Yizhe Hang , Heng Ge , Hongyuan Zha

Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\gamma < 1$, or in episodic settings, with…

Machine Learning · Computer Science 2019-02-11 Silviu Pitis

Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the…

Machine Learning · Computer Science 2026-05-28 Jiaxin Zhao , Weihang Pan , Xun Liang , Binbin Lin

In this paper, we study the global convergence of model-based and model-free policy gradient descent and natural policy gradient descent algorithms for linear quadratic deep structured teams. In such systems, agents are partitioned into a…

Multiagent Systems · Computer Science 2020-12-16 Vida Fathi , Jalal Arabneydi , Amir G. Aghdam

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

Machine Learning · Statistics 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

This paper deals with a network of computing agents aiming to solve an online optimization problem in a distributed fashion, i.e., by means of local computation and communication, without any central coordinator. We propose the gradient…

Optimization and Control · Mathematics 2023-09-13 Guido Carnevale , Francesco Farina , Ivano Notarnicola , Giuseppe Notarstefano

Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a…

Machine Learning · Computer Science 2020-11-04 Gavin McCracken , Colin Daniels , Rosie Zhao , Anna Brandenberger , Prakash Panangaden , Doina Precup

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer…

Multiagent Systems · Computer Science 2025-06-02 Pengcheng Dai , Yuanqiu Mo , Wenwu Yu , Wei Ren
‹ Prev 1 3 4 5 6 7 10 Next ›