Course Outline
Foundations of Reinforcement Learning and Agentic AI
- Sequential planning and decision-making in uncertain conditions
- Core RL elements: agents, environments, states, and reward mechanisms
- The function of RL within adaptive and agentic AI architectures
Markov Decision Processes (MDPs)
- Defining MDPs and exploring their key characteristics
- Value functions, the Bellman equations, and dynamic programming approaches
- Techniques for policy evaluation, improvement, and iterative refinement
Model-Free Reinforcement Learning
- Monte Carlo methods and Temporal-Difference (TD) learning
- Q-learning and SARSA algorithms
- Practical session: building tabular RL methods in Python
Deep Reinforcement Learning
- Integrating neural networks with RL for function approximation
- Deep Q-Networks (DQN) and the use of experience replay
- Actor-Critic frameworks and policy gradient methods
- Practical session: training agents using DQN and PPO with Stable-Baselines3
Exploration Techniques and Reward Design
- Managing the exploration-exploitation trade-off (using ε-greedy, UCB, and entropy methods)
- Crafting reward functions to prevent unintended system behaviors
- Strategies for reward shaping and curriculum learning
Advanced RL and Decision-Making Topics
- Multi-agent reinforcement learning and cooperative interaction strategies
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for secure deployment
Simulation Platforms and Performance Assessment
- Utilizing OpenAI Gym and developing custom environments
- Distinguishing between continuous and discrete action spaces
- Key metrics for evaluating agent performance, stability, and sample efficiency
Integrating RL into Agentic AI Architectures
- Merging reasoning capabilities with RL in hybrid agent designs
- Combining reinforcement learning with tool-utilizing agents
- Operational strategies for scaling and deployment
Capstone Project
- Designing and building a reinforcement learning agent for a simulated scenario
- Reviewing training performance and tuning hyperparameters
- Exhibiting adaptive behavior and decision-making in an agentic context
Conclusion and Future Directions
Requirements
- Advanced proficiency in Python programming
- A robust command of machine learning and deep learning principles
- Working knowledge of linear algebra, probability theory, and fundamental optimization techniques
Target Audience
- Specialists in reinforcement learning and applied AI research
- Developers in the fields of robotics and automation
- Engineering teams focused on building adaptive and agentic AI solutions
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
