中文
相关论文

相关论文: Off-policy Maximum Entropy Reinforcement Learning …

200 篇论文

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…

机器学习 · 计算机科学 2023-09-19 Han Zhong , Xun Deng , Ethan X. Fang , Zhuoran Yang , Zhaoran Wang , Runze Li

Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative blow-up factors with respect to the misspecification error of function approximation. Yet, the nature of such \emph{approximation factors} --…

机器学习 · 计算机科学 2023-12-18 Philip Amortila , Nan Jiang , Csaba Szepesvári

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

机器学习 · 计算机科学 2025-06-23 Kosuke Nakanishi , Akihiro Kubo , Yuji Yasui , Shin Ishii

Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant performance gap between…

机器学习 · 计算机科学 2021-05-07 Bozhidar Vasilev , Tarun Gupta , Bei Peng , Shimon Whiteson

This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating,…

机器学习 · 计算机科学 2022-12-02 Jinghan Wang , Mengdi Wang , Lin F. Yang

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

机器学习 · 计算机科学 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value…

机器学习 · 计算机科学 2020-02-19 Omer Gottesman , Yao Liu , Scott Sussex , Emma Brunskill , Finale Doshi-Velez

Off-policy actor-critic algorithms have shown strong potential in deep reinforcement learning for continuous control tasks. Their success primarily comes from leveraging pessimistic state-action value function updates, which reduce function…

机器学习 · 计算机科学 2025-08-21 Bahareh Tasdighi , Nicklas Werge , Yi-Shan Wu , Melih Kandemir

Model Predictive Control has been recently proposed as policy approximation for Reinforcement Learning, offering a path towards safe and explainable Reinforcement Learning. This approach has been investigated for Q-learning and actor-critic…

系统与控制 · 电气工程与系统科学 2020-04-06 Sebastien Gros , Mario Zanon

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

机器学习 · 计算机科学 2015-03-20 Thomas Degris , Martha White , Richard S. Sutton

We revisit the reduction of learning in adversarial Markov decision processes [MDPs] to adversarial learning based on $Q$--values; this reduction has been considered in a number of recent articles as one building block to perform policy…

机器学习 · 计算机科学 2025-05-20 Matthieu Jonckheere , Chiara Mignacco , Gilles Stoltz

The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) divergence for policy updates. However, this approach leads to an…

机器学习 · 计算机科学 2025-06-03 Yixian Zhang , Huaze Tang , Changxu Wei , Wenbo Ding

Training agents via off-policy deep reinforcement learning (RL) requires a large memory, named replay memory, that stores past experiences used for learning. These experiences are sampled, uniformly or non-uniformly, to create the batches…

机器学习 · 计算机科学 2022-12-27 Bumgeun Park , Taeyoung Kim , Woohyeon Moon , Luiz Felipe Vecchietti , Dongsoo Har

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the…

机器人学 · 计算机科学 2023-10-16 Shengjie Wang , Fengbo Lan , Xiang Zheng , Yuxue Cao , Oluwatosin Oseni , Haotian Xu , Tao Zhang , Yang Gao

In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning…

机器学习 · 计算机科学 2018-08-23 Dimitri P. Bertsekas

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

机器学习 · 计算机科学 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a…

机器人学 · 计算机科学 2022-11-11 Hai Nguyen , Andrea Baisero , Dian Wang , Christopher Amato , Robert Platt

The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in…

人工智能 · 计算机科学 2019-06-13 Elita Lobo , Scott Jordan

In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…

机器学习 · 计算机科学 2021-04-12 Ammar Fayad , Majd Ibrahim

Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…

机器学习 · 计算机科学 2022-07-05 Francesco Faccio , Aditya Ramesh , Vincent Herrmann , Jean Harb , Jürgen Schmidhuber