К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Decision-Making in Dynamic Environments · LearnSpace
Назад в каталог
courseraАнализ данных

Decision-Making in Dynamic Environments

Курс от LearnQuest
Начальный≈ 4.2 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This module immerses learners in the strategic world of multi-agent interactions, highlighting how intelligent agents collaborate and compete to solve complex problems. By mastering game theory principles, distributed training, and robust communication protocols, participants develop the expertise to deploy and scale AI agent solutions for dynamic, real-world environments. Learners build essential skills to design coordinated agent behaviors, optimize networked systems, and manage decentralized intelligence, positioning themselves to drive innovation in industries where collective decision-making delivers critical value.

Навыки, которые вы освоите

Agentic systemsResponsible AIReinforcement LearningAI OrchestrationAI SecurityDistributed ComputingMachine Learning MethodsDecision IntelligenceAgentic WorkflowsModel OptimizationArtificial IntelligenceData EthicsModel Training

Программа курса

3 модулей · 41 учебных материалов

01Reinforcement Learning Fundamentals15 материалов

Let's Get Started

Welcome to Decision-Making in Dynamic EnvironmentsВидеоLevel-Set with the CoachDIALOGUEReinforcement Learning FundamentalsВидео

Design custom reward shaping functions for targeted agent outcomes

Design custom reward shaping functionsВидео

Учитесь у экспертов

LearnQuest Network

Преподаватель курса

Decision-Making in Dynamic Environments
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 4.2 ч

3 модулей

Язык: Английский

Субтитры: Арабский, Французский, Итальянский, Бразильский португальский, Корейский, Испанский, Японский, Венгерский

Часть программы вашего университета
Action Story: When Reward Design BackfiresЧтение
Apply domain knowledge to craft high-impact reward signalsВидео
Validate reward functions with meta-learning evaluationВидео
Design custom reward shaping functions for targeted agent outcomesЗадание

Implement TD learning for real-time agent adaptation, policy optimization, and reward maximization

Implement TD learning for real-time agent adaptationВидеоOptimize agent policies with Q-learning and Monte Carlo methodsВидеоBalance exploration and exploitation to maximize cumulative rewardsВидеоLearning in Real Time: How Agents Adapt on the FlyDIALOGUE

Put it in Action: Reinforcement Learning Fundamentals

Role Play: Product Manager, AI Systems DivisionDIALOGUEReinforcement Learning FundamentalsЗаданиеFrom Fundamentals to InteractionsВидео
02Multi-Agent Interactions13 материалов

Let's Get Started

Multi-Agent InteractionsВидео

Model multi-agent interactions using Nash equilibrium concepts

Model multi-agent interactionsВидеоAction Story: When Collaboration Turns into CompetitionЧтениеEngineer efficient information sharing for collaborative tasksВидеоBuild competitive agent strategies to dominate market simulationsВидеоModel multi-agent interactions using Nash equilibrium conceptsЗадание

Scale agent training with distributed computing frameworks

Scale agent trainingВидеоImplement peer-to-peer communication protocols for agent teamsВидеоManage data consistency across decentralized agent networksВидеоTraining at Scale: Smarter Systems Through Shared PowerDIALOGUEScale agent training with distributed computing frameworksЗадание

Put it in Action: Multi-Agent Interactions

Role Play: Leading Multi-Agent Teams to Work SmarterDIALOGUEMulti-Agent InteractionsЗадание
03Adaptation, Fairness, and Robustness13 материалов

Let's Get Started

Adaptation, Fairness, and RobustnessВидео

Apply transfer learning techniques to handle dynamic data streams

Apply transfer learning techniques to handle dynamic data streamsВидеоAction Story: When Yesterday’s Model Stops Making SenseЧтениеDetect concept drift for timely model recalibrationВидеоIntegrate continual learning pipelines for real-world relevanceВидеоApply transfer learning techniques to handle dynamic data streamsЗадание

Implement fairness constraints using open-source toolkits

Implement fairness constraints using open-source toolkitsВидеоEvaluate agents for bias and discriminatory behaviorsВидеоDefend agents against adversarial attacks with robust design patternsВидеоImplement fairness constraints using open-source toolkitsЗадание

Put it in Action: Adaptation, Fairness, and Robustness

Role Play: Managing Change in Real-World AIDIALOGUEAdaptation, Fairness, and RobustnessЗаданиеFrom Decision-Making to DeploymentВидео