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.
Duration 28 hours
Course Outline
Introduction to Reinforcement Learning and Agentic AI
- Strategies for decision-making under uncertainty and sequential planning
- Core components of RL: agents, environments, states, and reward signals
- The role of RL in enhancing adaptive and agentic AI systems
Markov Decision Processes (MDPs)
- Formal definitions and key properties of MDPs
- Value functions, Bellman equations, and the application of dynamic programming
- Techniques for policy evaluation, improvement, and iterative refinement
Model-Free Reinforcement Learning
- Overview of Monte Carlo and Temporal-Difference (TD) learning methods
- Deep dive into Q-learning and SARSA algorithms
- Practical exercise: implementing tabular RL methods in Python
Deep Reinforcement Learning
- Leveraging neural networks in RL for advanced function approximation
- Deep Q-Networks (DQN) and the mechanism of experience replay
- Exploring Actor-Critic architectures and policy gradient methods
- Practical exercise: training an agent using DQN and PPO with Stable-Baselines3
Exploration Strategies and Reward Shaping
- Balancing exploration against exploitation using \u03b5-greedy, UCB, and entropy-based methods
- Designing effective reward functions and mitigating unintended behaviors
- Applying reward shaping and curriculum learning techniques
Advanced Topics in RL and Decision-Making
- Multi-agent reinforcement learning and the development of cooperative strategies
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for safer deployment scenarios
Simulation Environments and Evaluation
- Utilizing OpenAI Gym and developing custom simulation environments
- Distinguishing between continuous and discrete action spaces
- Establishing metrics for assessing agent performance, stability, and sample efficiency
Integrating RL into Agentic AI Systems
- Combining reasoning capabilities with RL in hybrid agent architectures
- Integrating reinforcement learning with tool-using agents
- Navigating operational considerations for system scaling and deployment
Capstone Project
- Design and implement a reinforcement learning agent for a specific simulated task
- Analyze training performance and fine-tune hyperparameters for optimal results
- Demonstrate adaptive behavior and complex decision-making within an agentic context
Summary and Next Steps
Requirements
- Advanced proficiency in Python programming
- A robust understanding of machine learning and deep learning concepts
- Familiarity with linear algebra, probability theory, and fundamental optimization methods
Target Audience
- Reinforcement learning engineers and applied AI researchers
- Developers specializing in robotics and automation
- Engineering teams focused on building adaptive and agentic AI systems
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
