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 in Agentic AI
- Planning and decision-making under uncertainty
- Essential RL elements: agents, environments, states, and reward signals
- The function of RL in fostering adaptive and agentic AI capabilities
Markov Decision Processes (MDPs)
- Formal structure and characteristics of MDPs
- Value functions, Bellman equations, and dynamic programming techniques
- Techniques for policy evaluation, refinement, and iterative improvement
Model-Free Reinforcement Learning
- Monte Carlo methods and Temporal-Difference (TD) learning
- Algorithms for Q-learning and SARSA
- Practical implementation of tabular RL methods using Python
Deep Reinforcement Learning
- Integrating neural networks for function approximation in RL
- Deep Q-Networks (DQN) and experience replay mechanisms
- Actor-Critic architectures and policy gradient strategies
- Practical exercise: Training agents with DQN and PPO using Stable-Baselines3
Exploration Tactics and Reward Design
- Strategies for balancing exploration vs. exploitation (ε-greedy, UCB, entropy-based methods)
- Crafting reward functions to mitigate unintended behaviors
- Reward shaping techniques and curriculum learning approaches
Advanced Concepts in RL and Decision-Making
- Multi-agent reinforcement learning and cooperative frameworks
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for enhanced deployment safety
Simulation Platforms and Performance Assessment
- Leveraging OpenAI Gym and developing custom environments
- Navigating continuous vs. discrete action spaces
- Evaluating agent performance, stability, and sample efficiency
Embedding RL into Agentic AI Architectures
- Merging reasoning capabilities with RL in hybrid agent designs
- Integrating reinforcement learning with tool-using agents
- Operational strategies for scaling and production deployment
Capstone Project
- Architect and develop an RL agent for a simulated objective
- Evaluate training outcomes and refine hyperparameters
- Illustrate adaptive decision-making within an agentic framework
Concluding Remarks and Future Directions
Requirements
- Advanced command of Python programming
- Comprehensive grasp of machine learning and deep learning principles
- Competence in linear algebra, probability, and fundamental optimization techniques
Intended Audience
- Reinforcement learning engineers and applied AI researchers
- Developers specializing in robotics and automation
- Engineering teams focused on 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
