中文
相关论文

相关论文: Provably Efficient Primal-Dual Reinforcement Learn…

200 篇论文

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

机器学习 · 计算机科学 2024-02-26 Zhishuai Liu , Pan Xu

We study model-free reinforcement learning (RL) in non-stationary finite-horizon episodic Markov decision processes (MDPs) without prior knowledge of the non-stationarity. We focus on the piecewise stationary (PS) setting, where both…

机器学习 · 计算机科学 2026-05-13 Argyrios Gerogiannis , Yu-Han Huang , Venugopal V. Veeravalli

Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and…

机器人学 · 计算机科学 2024-03-07 Zhaorun Chen , Zhuokai Zhao , Tairan He , Binhao Chen , Xuhao Zhao , Liang Gong , Chengliang Liu

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

人工智能 · 计算机科学 2019-11-26 Nils Jansen , Bettina Könighofer , Sebastian Junges , Alexandru C. Serban , Roderick Bloem

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We…

机器学习 · 计算机科学 2020-12-02 Fei Feng , Ruosong Wang , Wotao Yin , Simon S. Du , Lin F. Yang

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision…

机器学习 · 计算机科学 2020-08-18 Akifumi Wachi , Yanan Sui

Robotic systems operating in dynamic and uncertain environments increasingly require planners that satisfy complex task sequences while adhering to strict temporal constraints. Metric Interval Temporal Logic (MITL) offers a formal and…

机器人学 · 计算机科学 2026-01-05 Zhaoan Wang , Junchao Li , Mahdi Mohammad , Shaoping Xiao

Reinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. However, in many real-world RL problems, besides optimizing the main objectives, the agent is…

机器学习 · 计算机科学 2021-07-30 Ashkan B. Jeddi , Nariman L. Dehghani , Abdollah Shafieezadeh

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and…

机器学习 · 计算机科学 2024-03-12 Vincent Leon , S. Rasoul Etesami

This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). To this end, we extend the Neural Combinatorial Optimization (NCO) theory in order to deal with constraints in…

机器学习 · 计算机科学 2020-06-23 Ruben Solozabal , Josu Ceberio , Martin Takáč

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction.…

机器学习 · 计算机科学 2023-07-04 Weiye Zhao , Tairan He , Rui Chen , Tianhao Wei , Changliu Liu

An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process…

机器学习 · 计算机科学 2021-06-29 Mónika Farsang , Luca Szegletes

Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired…

机器学习 · 统计学 2022-01-24 Koulik Khamaru , Eric Xia , Martin J. Wainwright , Michael I. Jordan

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL)…

系统与控制 · 电气工程与系统科学 2021-09-29 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

This work provides a state-of-the-art survey of continual safe online reinforcement learning (COSRL) methods. We discuss theoretical aspects, challenges, and open questions in building continual online safe reinforcement learning…

机器学习 · 计算机科学 2026-01-09 Timofey Tomashevskiy

High-level penetration of intermittent renewable energy sources (RESs) has introduced significant uncertainties into modern power systems. In order to rapidly and economically respond to the fluctuations of power system operating state,…

系统与控制 · 电气工程与系统科学 2023-08-08 Pengfei Wu , Chen Chen , Dexiang Lai , Jian Zhong

Reinforcement learning (RL) is currently one of the most prominent methods for optimizing dynamical systems, with breakthrough results across various fields. The framework is based on the concept of a Markov decision process (MDP), leading…

最优化与控制 · 数学 2025-11-17 Rene Carmona , Mathieu Lauriere

Many reinforcement learning (RL) environments in practice feature enormous state spaces that may be described compactly by a "factored" structure, that may be modeled by Factored Markov Decision Processes (FMDPs). We present the first…

机器学习 · 计算机科学 2022-03-08 Zihao Deng , Siddartha Devic , Brendan Juba

Safe reinforcement learning tasks are a challenging domain despite being very common in the real world. The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In…

机器学习 · 计算机科学 2024-08-30 Zihan Zhou , Jonathan Booher , Khashayar Rohanimanesh , Wei Liu , Aleksandr Petiushko , Animesh Garg

Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…

机器学习 · 计算机科学 2022-06-22 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson