Advanced Reinforcement Learning

Reinforcement Learning Specialization

This certification course provides policymakers, analysts, and public sector professionals with the knowledge to use AI responsibly. It covers governance frameworks, ethics, and real-world applications from predictive analytics to public safety.

An 8-course professional certificate series by IBM that teaches you to build next-generation AI systems using Retrieval-Augmented Generation and Agentic AI. You'll gain skills in LangChain, OpenAI, and responsible AI.

A comprehensive program designed to prepare you for the field of artificial intelligence and machine learning. It covers designing scalable AI & ML infrastructure, core algorithms, AI agent development, and leveraging cloud-based AI & ML services, specifically through Microsoft Azure. A capstone project simulates real-world challenges.

This specialization from IBM experts teaches how to develop agentic AI systems using modern frameworks and workflow patterns. You'll work with Lang Graph to create agents with memory and logic, explore self-improving agents, and design multi-agent systems with frameworks like CrewAI, AG2 (Auto Gen), and BeeAI.

This course covers the fundamentals of unsupervised learning techniques such as clustering and dimensionality reduction to make sense of large, unlabeled datasets. You will learn to implement k-means and hierarchical clustering.

This course, part of the TinyML Professional Certificate series, delves into the practical applications of Tiny Machine Learning. Students explore the code behind widely used TinyML applications like keyword spotting, visual wake words, and anomaly detection. The course uses real-world industry applications to illustrate the principles of TinyML.

This three-course professional certificate program, offered by Harvard University and Google TensorFlow, provides a deep dive into the emerging field of TinyML. It covers the essential language of TinyML, its real-world applications, and the practical deployment of machine learning models on resource-constrained embedded systems. The program emphasizes hands-on experience using a kit that includes an Arduino board.

This course introduces the fundamentals of reinforcement learning, guiding learners on how to frame RL problems and tackle classic examples. It covers basic algorithms and progresses to using function approximation with deep learning. It also features 'Project Malmo' for AI experimentation within Minecraft.

This course provides guidance on balancing AI innovation with risk mitigation, covering frameworks for AI governance, Safety by Design strategies, risk assessment methods, red teaming approaches, and regulatory compliance essentials. It is designed for professionals in Trust & Safety, AI engineering, policy, and brand management.

The world's first & top-rated AI Product Management Certification, taken by 20k+ professionals. Learn from Marily & experts from OpenAI, Anthropic, Amazon & Meta through 65 lessons, 17 hours live content, hands-on exercises, and group coaching.

Reinforcement Learning: Complete Course with Python

This course covers Support Vector Machines (SVM) from basic to advanced kernel-based models. It is designed for those who want to apply machine learning to real-world business problems and includes topics like hyperparameter tuning and model performance evaluation.

This course focuses on creating and evaluating human data for SFT, RLHF, and red-teaming. It also covers mastering AI data quality and safety standards, which is a crucial aspect of data curation for AI models.

LangChain Agent Development Mastery

University of Alberta Fundamentals of Reinforcement Learning

Master RL algorithms from Q-learning to PPO. Build agents that learn from interaction and make optimal decisions.

Comprehensive course on Reinforcement Learning on AWS taught by AWS. Part of AWS ML curriculum.