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
- Decision-making under uncertainty and the principles of sequential planning
- Core RL elements: agents, environments, states, and reward mechanisms
- The role of RL in fostering adaptive and agentic AI capabilities
Markov Decision Processes (MDPs)
- Formal definitions and key properties of MDPs
- Value functions, Bellman equations, and dynamic programming approaches
- Cycles of policy evaluation, improvement, and iteration
Model-Free Reinforcement Learning
- Monte Carlo methods and Temporal-Difference (TD) learning
- Q-learning and SARSA algorithms
- Practical session: Implementing 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 architectures and policy gradient methods
- Practical session: Training agents with DQN and PPO using Stable-Baselines3
Exploration Strategies and Reward Shaping
- Balancing exploration against exploitation (ε-greedy, UCB, and entropy-based methods)
- Crafting reward functions to prevent unintended agent behaviors
- Techniques in reward shaping and curriculum learning
Advanced RL and Decision-Making Concepts
- Multi-agent reinforcement learning and cooperative strategies
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for enhanced safety in deployment
Simulation Environments and Performance Evaluation
- Leveraging OpenAI Gym and developing custom environments
- Distinguishing between continuous and discrete action spaces
- Key metrics for assessing agent performance, stability, and sample efficiency
Integrating RL into Agentic AI Systems
- Merging reasoning capabilities with RL in hybrid agent architectures
- Incorporating reinforcement learning into tool-using agents
- Operational strategies for scaling and production deployment
Capstone Project
- Design and build a reinforcement learning agent for a specific simulated task
- Analyze training performance and fine-tune hyperparameters
- Demonstrate adaptive decision-making within an agentic framework
Summary and Recommended Next Steps
Requirements
- Advanced proficiency in Python programming
- A robust grasp of machine learning and deep learning principles
- Working knowledge of linear algebra, probability theory, and fundamental optimization techniques
Target Audience
- Reinforcement learning specialists and applied AI researchers
- Developers focused on robotics and automation
- Engineering teams developing adaptive and agentic AI solutions
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
