📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Reinforcement Learning for Real-World Applications, from foundations to a certified capstone project.
Formulation
• States, actions, rewards, transitions and the discount factor
• Reward specification and the reward hacking that follows a careless definition
• Why most real problems are partially observed rather than clean MDPs
Foundations
• Dynamic programming, Monte Carlo and temporal difference learning
• Q-learning and SARSA, and the exploration-exploitation trade-off
• Function approximation and the instability it introduces
Deep RL
• DQN with replay buffers and target networks, and why both are needed
• Policy gradients, PPO and actor-critic architectures
• Sample inefficiency as the dominant practical obstacle
Simulation
• Building a simulator with Gymnasium and validating that it matches reality
• The sim-to-real gap and domain randomisation as a partial answer
• Offline RL when only logged data is available
Deployment
• Robotics, control, recommendation and operations as the realistic domains
• Safe RL: constraints, shielding and fallback to a known-good policy
• Monitoring a deployed policy and detecting distribution shift
Earn government-registered certification in Reinforcement Learning for Real-World Applications
e-Certificate and e-Marksheet issued on successful completion.
