When will I have access to the lectures and assignments?

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

What will I get if I subscribe to this Specialization?

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Is financial aid available?

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Decision-Making in Dynamic Environments

Ce cours n'est pas disponible en Français (France)

Nous sommes actuellement en train de le traduire dans plus de langues. Consultez les langues disponibles.

Decision-Making in Dynamic Environments

Ce cours fait partie de Spécialisation "Build AI Agents with Practical App Design"

Instructeur : LearnQuest Network

Inclus avec

3 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Débutant

Expérience recommandée

3 heures à compléter

Planning flexible

Apprenez à votre propre rythme

3 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Débutant

Expérience recommandée

3 heures à compléter

Planning flexible

Apprenez à votre propre rythme

Compétences que vous acquerrez

Catégorie : Artificial Intelligence
Catégorie : Machine Learning Methods
Catégorie : Data Ethics
Catégorie : Responsible AI
Catégorie : Reinforcement Learning
Catégorie : Distributed Computing
Catégorie : Agentic systems
Catégorie : Decision Intelligence
Catégorie : Model Training
Catégorie : AI Security

Détails à connaître

Certificat partageable

Ajouter à votre profil LinkedIn

Évaluations

8 affectations¹

Noté par l'IA voir l'avis de non-responsabilité

Enseigné en Anglais

91%

of learners achieved a positive career outcome

Découvrez comment les employés des entreprises prestigieuses maîtrisent des compétences recherchées

En savoir plus sur Coursera pour les affaires

logos de Petrobras, TATA, Danone, Capgemini, P&G et L'Oreal

Élaborez votre expertise du sujet

Ce cours fait partie de la Spécialisation "Build AI Agents with Practical App Design"

Lorsque vous vous inscrivez à ce cours, vous êtes également inscrit(e) à cette Spécialisation.

Apprenez de nouveaux concepts auprès d'experts du secteur
Acquérez une compréhension de base d'un sujet ou d'un outil
Développez des compétences professionnelles avec des projets pratiques
Obtenez un certificat professionnel partageable

Il y a 3 modules dans ce cours

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.

Détails du module

Reinforcement learning empowers autonomous AI agents to optimize decisions in complex, changing environments. In this module, learners will develop foundational expertise in designing reward structures, implementing sequential learning methods, and tuning agent behaviors for impact. Through practical case studies and hands-on exercises, participants will master how to align agent incentives with organizational goals, leverage temporal difference learning for adaption, and engineer strategies that balance exploration with exploitation. Prepare to drive real-world innovation by building robust RL systems that respond intelligently to evolving business needs.

Inclus

9 vidéos1 lecture2 devoirs

9 vidéosTotal 16 minutes

Welcome to Decision-Making in Dynamic Environments3 minutes
Reinforcement Learning Fundamentals2 minutes
Design custom reward shaping functions2 minutes
Apply domain knowledge to craft high-impact reward signals2 minutes
Validate reward functions with meta-learning evaluation1 minute
Implement TD learning for real-time agent adaptation2 minutes
Optimize agent policies with Q-learning and Monte Carlo methods2 minutes
Balance exploration and exploitation to maximize cumulative rewards1 minute
From Fundamentals to Interactions2 minutes

1 lectureTotal 5 minutes

Action Story: When Reward Design Backfires5 minutes

2 devoirsTotal 36 minutes

Reinforcement Learning Fundamentals26 minutes
Design custom reward shaping functions for targeted agent outcomes10 minutes

Inclus

7 vidéos1 lecture3 devoirs

7 vidéosTotal 9 minutes

Multi-Agent Interactions2 minutes
Model multi-agent interactions2 minutes
Engineer efficient information sharing for collaborative tasks1 minute
Build competitive agent strategies to dominate market simulations1 minute
Scale agent training1 minute
Implement peer-to-peer communication protocols for agent teams1 minute
Manage data consistency across decentralized agent networks1 minute

1 lectureTotal 5 minutes

Action Story: When Collaboration Turns into Competition5 minutes

3 devoirsTotal 42 minutes

Multi-Agent Interactions26 minutes
Model multi-agent interactions using Nash equilibrium concepts10 minutes
Scale agent training with distributed computing frameworks6 minutes

This module prepares learners to build agents that thrive in the constantly evolving, complex realities of business and society. By mastering adaptation to data and environment changes, enforcing fairness in decision processes, and designing defensively against adversarial threats, participants will develop the expertise to deploy resilient, ethical AI solutions. Learners acquire powerful tools and evidence-based strategies that enable robust agent performance in unpredictable markets, mission-critical environments, and diverse global contexts.

Inclus

8 vidéos1 lecture3 devoirs

8 vidéosTotal 11 minutes

Adaptation, Fairness, and Robustness2 minutes
Apply transfer learning techniques to handle dynamic data streams1 minute
Detect concept drift for timely model recalibration1 minute
Integrate continual learning pipelines for real-world relevance1 minute
Implement fairness constraints using open-source toolkits1 minute
Evaluate agents for bias and discriminatory behaviors1 minute
Defend agents against adversarial attacks with robust design patterns1 minute
From Decision-Making to Deployment2 minutes

1 lectureTotal 5 minutes

Action Story: When Yesterday’s Model Stops Making Sense5 minutes

3 devoirsTotal 32 minutes

Adaptation, Fairness, and Robustness16 minutes
Apply transfer learning techniques to handle dynamic data streams10 minutes
Implement fairness constraints using open-source toolkits6 minutes

Obtenez un certificat professionnel

Ajoutez ce titre à votre profil LinkedIn, à votre curriculum vitae ou à votre CV. Partagez-le sur les médias sociaux et dans votre évaluation des performances.