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 in uncertain conditions and sequential planning
- Core RL elements: agents, environments, states, and reward signals
- The significance of RL in adaptive and agentic AI frameworks
Markov Decision Processes (MDPs)
- Formal structures and characteristics of MDPs
- Value functions, Bellman equations, and dynamic programming approaches
- Processes for policy evaluation, refinement, and iterative improvement
Model-Free Reinforcement Learning
- Monte Carlo methods and Temporal-Difference (TD) learning
- Q-learning and SARSA algorithms
- Practical exercise: coding tabular RL methods in Python
Deep Reinforcement Learning
- Integrating neural networks with RL for function approximation
- Deep Q-Networks (DQN) and the experience replay mechanism
- Actor-Critic structures and policy gradient methods
- Practical exercise: training agents with DQN and PPO using Stable-Baselines3
Exploration Techniques and Reward Design
- Managing the balance between exploration and exploitation (\u03b5-greedy, UCB, entropy-based strategies)
- Crafting reward functions and mitigating unintended agent behaviors
- Strategies for reward shaping and curriculum learning
Advanced Concepts in RL and Decision-Making
- Multi-agent reinforcement learning and cooperative game strategies
- Hierarchical reinforcement learning and the options framework
- Offline RL and imitation learning for enhanced deployment safety
Simulation Platforms and Performance Assessment
- Implementing OpenAI Gym and custom environment setups
- Differentiating between continuous and discrete action spaces
- Evaluation metrics for agent efficacy, stability, and sample efficiency
Embedding RL into Agentic AI Frameworks
- Merging reasoning capabilities with RL in hybrid agent structures
- Aligning reinforcement learning with tool-using agent architectures
- Operational factors for scaling and production deployment
Capstone Project
- Architect and build a reinforcement learning agent for a defined simulation task
- Review training outcomes and fine-tune hyperparameters
- Illustrate adaptive decision-making within an agentic environment
Conclusions and Future Directions
Requirements
- Advanced proficiency in Python development
- Robust knowledge of machine learning and deep learning principles
- Competence in linear algebra, probability theory, and fundamental optimization techniques
Target Audience
- Reinforcement learning specialists and applied AI researchers
- Developers focused on robotics and automation
- Engineering groups 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
