Course Outline
Introduction to Reinforcement Learning and Agentic AI
- Decision-making under uncertainty and sequential planning
- Key components of RL: agents, environments, states, and rewards
- Role of RL in adaptive and agentic AI systems
Markov Decision Processes (MDPs)
- Formal definition and properties of MDPs
- Value functions, Bellman equations, and dynamic programming
- Policy evaluation, improvement, and iteration
Model-Free Reinforcement Learning
- Monte Carlo and Temporal-Difference (TD) learning
- Q-learning and SARSA
- Hands-on: implementing tabular RL methods in Python
Deep Reinforcement Learning
- Combining neural networks with RL for function approximation
- Deep Q-Networks (DQN) and experience replay
- Actor-Critic architectures and policy gradients
- Hands-on: training an agent using DQN and PPO with Stable-Baselines3
Exploration Strategies and Reward Shaping
- Balancing exploration vs. exploitation (ε-greedy, UCB, entropy methods)
- Designing reward functions and avoiding unintended behaviors
- Reward shaping and curriculum learning
Advanced Topics in RL and Decision-Making
- Multi-agent reinforcement learning and cooperative strategies
- Hierarchical reinforcement learning and options framework
- Offline RL and imitation learning for safer deployment
Simulation Environments and Evaluation
- Using OpenAI Gym and custom environments
- Continuous vs. discrete action spaces
- Metrics for agent performance, stability, and sample efficiency
Integrating RL into Agentic AI Systems
- Combining reasoning and RL in hybrid agent architectures
- Integrating reinforcement learning with tool-using agents
- Operational considerations for scaling and deployment
Capstone Project
- Design and implement a reinforcement learning agent for a simulated task
- Analyze training performance and optimize hyperparameters
- Demonstrate adaptive behavior and decision-making in an agentic context
Summary and Next Steps
Requirements
- Strong proficiency in Python programming
- Solid understanding of machine learning and deep learning concepts
- Familiarity with linear algebra, probability, and basic optimization methods
Audience
- Reinforcement learning engineers and applied AI researchers
- Robotics and automation developers
- Engineering teams working on adaptive and agentic AI systems
Testimonials (3)
Strong confirmation that current LLMs are deployable for customer projects when the proper setup is in place.
Oliver Fromm
Course - Agentic AI for Enterprise Applications
Machine Translated
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
The mix of theory and practice and of high level and low level perspectives
