中文
相关论文

相关论文: Minimum-Delay Adaptation in Non-Stationary Reinfor…

200 篇论文

Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…

机器学习 · 计算机科学 2022-04-21 Jiafan He , Dongruo Zhou , Quanquan Gu

Most reinforcement learning algorithms are based on a key assumption that Markov decision processes (MDPs) are stationary. However, non-stationary MDPs with dynamic action space are omnipresent in real-world scenarios. Yet problems of…

机器学习 · 计算机科学 2023-04-04 Jiaqi Ye , Xiaodong Li , Pangjing Wu , Feng Wang

One key challenge for multi-task Reinforcement learning (RL) in practice is the absence of task indicators. Robust RL has been applied to deal with task ambiguity, but may result in over-conservative policies. To balance the worst-case…

机器学习 · 计算机科学 2022-10-25 Mengdi Xu , Peide Huang , Yaru Niu , Visak Kumar , Jielin Qiu , Chao Fang , Kuan-Hui Lee , Xuewei Qi , Henry Lam , Bo Li , Ding Zhao

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

机器学习 · 计算机科学 2024-09-27 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually…

机器学习 · 计算机科学 2018-05-25 Qingyun Wu , Naveen Iyer , Hongning Wang

A common setting of reinforcement learning (RL) is a Markov decision process (MDP) in which the environment is a stochastic discrete-time dynamical system. Whereas MDPs are suitable in such applications as video-games or puzzles, physical…

机器人学 · 计算机科学 2022-11-29 Pavel Osinenko , Dmitrii Dobriborsci , Grigory Yaremenko , Georgiy Malaniya

Markov decision processes (MDPs) are formal models commonly used in sequential decision-making. MDPs capture the stochasticity that may arise, for instance, from imprecise actuators via probabilities in the transition function. However, in…

人工智能 · 计算机科学 2023-06-21 Marnix Suilen , Thiago D. Simão , David Parker , Nils Jansen

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…

机器学习 · 计算机科学 2024-09-10 Feng Zhu , Robert W. Heath , Aritra Mitra

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

This paper proposes a multi-agent reinforcement learning based medium access framework for wireless networks. The access problem is formulated as a Markov Decision Process (MDP), and solved using reinforcement learning with every network…

机器学习 · 计算机科学 2021-04-30 Hrishikesh Dutta , Subir Biswas

To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider…

机器学习 · 计算机科学 2018-11-29 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

机器学习 · 计算机科学 2019-11-05 Andrea Zanette , Emma Brunskill

Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set…

人工智能 · 计算机科学 2017-06-06 Leonardo A. Ferreira , Reinaldo A. C. Bianchi , Paulo E. Santos , Ramon Lopez de Mantaras

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…

机器学习 · 计算机科学 2021-01-05 Baiming Chen , Zuxin Liu , Jiacheng Zhu , Mengdi Xu , Wenhao Ding , Ding Zhao

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime…

机器学习 · 计算机科学 2023-02-22 Heyang Zhao , Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are…

机器学习 · 计算机科学 2022-01-04 Arun Raman , Keerthan Shagrithaya , Shalabh Bhatnagar

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

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, outside of restrictive…

机器学习 · 计算机科学 2024-10-24 Philip Amortila , Dylan J. Foster , Nan Jiang , Akshay Krishnamurthy , Zakaria Mhammedi

We study the problem of zero-delay coding for the transmission of a Markov source over a noisy channel with feedback and present a reinforcement learning solution which is guaranteed to achieve near-optimality. To this end, we formulate the…

最优化与控制 · 数学 2025-10-07 Liam Cregg , Fady Alajaji , Serdar Yuksel

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…