Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Foundations of Reinforcement Learning and Agentic AI
- Navigating decision-making under uncertainty and sequential planning
- Core RL components: agents, environments, states, and reward structures
- The function of RL in shaping adaptive and agentic AI systems
Markov Decision Processes (MDPs)
- Defining the formal properties and structure of MDPs
- Understanding value functions, Bellman equations, and dynamic programming
- Processes for policy evaluation, improvement, and iteration
Model-Free Reinforcement Learning
- Exploring Monte Carlo and Temporal-Difference (TD) learning methods
- Techniques for Q-learning and SARSA
- Practical application: Implementing tabular RL methods in Python
Deep Reinforcement Learning
- Merging neural networks with RL for advanced function approximation
- Deep Q-Networks (DQN) and the concept of experience replay
- Actor-Critic architectures and policy gradient methods
- Practical application: Training agents with DQN and PPO using Stable-Baselines3
Exploration Strategies and Reward Design
- Striking a balance between exploration and exploitation (including ε-greedy, UCB, and entropy-based methods)
- Crafting effective reward functions to mitigate unintended behaviors
- Strategies for reward shaping and curriculum learning
Advanced Concepts in RL and Decision-Making
- Multi-agent reinforcement learning and cooperative strategies
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for enhanced deployment safety
Simulation Environments and Performance Evaluation
- Utilizing OpenAI Gym and developing custom environments
- Distinguishing between continuous and discrete action spaces
- Key metrics for assessing agent performance, stability, and sample efficiency
Integration of RL into Agentic AI Systems
- Combining reasoning capabilities with RL in hybrid agent architectures
- Integrating reinforcement learning with tool-using agents
- Operational strategies for scaling and production deployment
Capstone Project
- Designing and implementing a reinforcement learning agent for a specific simulated task
- Analyzing training performance and refining hyperparameters
- Demonstrating adaptive decision-making behavior within an agentic context
Conclusion and Future Directions
Requirements
- Advanced proficiency in Python programming
- A robust grasp of machine learning and deep learning fundamentals
- Working knowledge of linear algebra, probability theory, and basic optimization techniques
Target Audience
- Reinforcement learning engineers and applied AI researchers
- Developers specializing in robotics and automation
- Engineering teams developing adaptive and agentic AI systems
28 Hours
Testimonials (3)
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
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
