搜索结果: 1-15 共查到“reinforcement”相关记录21条 . 查询时间(0.046 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Markov decision process and reinforcement learning for intelligent
智能 马尔可夫 决策过程 强化学习
2023/4/28
本次讲座主要针对智能运维中的建模优化问题。首先基于前期研究，我将讨论基于马尔可夫决策过程的有限周期的视情维护策略。考虑二元件系统以及系统元件的退化过程具有随机相关性，用二元伽马过程来描述系统退化过程。系统元件服从周期性检测，当元件的退化程度超过预防性维护阈值时，其会被替换。该维护问题可以表示成马尔可夫决策过程并可用动态规划来求解。不同于无限周期的维护策略，有限周期的最优策略是动态的，其在每次检测都...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Markov decision process and reinforcement learning for intelligent operation and maintenance
智能 马尔可夫 决策过程 强化学习
2023/4/28
本次讲座主要针对智能运维中的建模优化问题。首先基于前期研究，我将讨论基于马尔可夫决策过程的有限周期的视情维护策略。考虑二元件系统以及系统元件的退化过程具有随机相关性，用二元伽马过程来描述系统退化过程。系统元件服从周期性检测，当元件的退化程度超过预防性维护阈值时，其会被替换。该维护问题可以表示成马尔可夫决策过程并可用动态规划来求解。不同于无限周期的维护策略，有限周期的最优策略是动态的，其在每次检测都...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Reinforcement Learning-Based Event-Driven Adaptive Cooperative Control of Heterogeneous Multiagent Systems
强化学习 异构多智能体系统 事件驱动 自适应 协同控制
2023/5/17
This talk focuses on the even-triggered cooperative control problem of heterogeneous multi-agent systems (MASs) using data-based reinforcement learning (RL) algorithm. To lower the communication and c...
第1期“互联”学术沙龙——“Ten Key for Reinforcement Learning and Optimal Control”顺利举行（图）
互联 学术沙龙 强大学习 机器学习
2022/12/29
强大学习（Reinforcement Learning, RL），又称再励学习、评价学习或增强学习，是机器学习的范式和方法论之一，用于描述和解决智能体（agent）在与环境的交互过程中通过学习策略以达成回报最大化或实现特定目标的问题。在过去的几十年中，强化学习在许多领域中取得了巨大的成功，尤其是由谷歌（Google）旗下DeepMind公司戴密斯·哈萨比斯领衔的团队开发的AlphaGo，它是第一个...
Reinforcement Learning (RL) has achieved many successes over the years in training autonomous agents to perform simple tasks. However, it takes a long time to learn a solution and this solution can us...
Kernel-Based Reinforcement Learning in Average-Cost Problems
Average–cost problem dynamic programming kernel smoothing local averaging Markov decision process (MDP)
2015/7/8
Reinforcement learning (RL) is concerned with the identification of optimal controls in Markov decision processes (MDPs) where no explicit model of the transition probabilities is available. Many exis...
ADAPTIVE STEP-SIZES FOR REINFORCEMENT LEARNING
reinforcement learning machine learning step-size learning rate evaluation adaptive
2014/12/18
The central theme motivating this dissertation is the desire to develop reinforcement learning algorithms that “just work” regardless of the domain in which they are applied. The largest impediment to...
Electric Power Market Modeling with Multi-Agent Reinforcement Learning
Electric Power Market Modeling Multi-Agent Reinforcement Learning
2014/10/22
Agent-based modeling (ABM) is a relatively new tool for use in electric power market research. At heart are software agents representing real-world stakeholders in the industry: utilities, power produ...
Reinforcement Learning for the Soccer Dribbling Task
Reinforcement Learning Soccer Dribbling Task
2013/6/17
We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball,...
This paper proposes an online tree-based Bayesian approach for reinforcement learning. For inference, we employ a generalised context tree model. This defines a distribution on multivariate Gaussian p...
Regret Bounds for Reinforcement Learning with Policy Advice
Regret Bounds Reinforcement LearningPolicy Advice
2013/6/13
In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with p...
ABC Reinforcement Learning
ABC Reinforcement Learning
2013/4/28
This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is that we only require a prio...
Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems
Efficient Reinforcement Learning High Dimensional Linear Quadratic Systems
2013/4/28
We study the problem of adaptive control of a high dimensional linear quadratic (LQ) system. Previous work established the asymptotic convergence to an optimal controller for various adaptive control ...
A Greedy Approximation of Bayesian Reinforcement Learning with Probably Optimistic Transition Model
Reinforcement Learning Uncertain Knowledge Probabilistic Reasoning Optimal Behavior in Polynomial Time
2013/5/2
Bayesian Reinforcement Learning (RL) is capable of not only incorporating domain knowledge, but also solving the exploration-exploitation dilemma in a natural way. As Bayesian RL is intractable except...
Monte-Carlo utility estimates for Bayesian reinforcement learning
Monte-Carlo estimates Bayesian reinforcement learning
2013/5/2
This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct ...