AI & Machine Learning
Generative AI & Large Language Models
How large language models really work — and how to build reliable products on top of them.
5 free lectures$69₹4,499
AI & Machine Learning
Reinforcement Learning
Reinforcement learning powers game-playing agents, robotics, recommendation and the fine-tuning of large language models. Pull slot-machine levers to feel the explore–exploit dilemma, watch values ripple through a grid world, and see a robot learn a route in 3D with Q-learning.
What you’ll learn
- Frame a problem as an agent, environment, actions, states and rewards
- Balance exploration and exploitation with ε-greedy, UCB and Thompson sampling
- Model sequential decisions as Markov decision processes
- Compute value functions with the Bellman equation and dynamic programming
- Train agents with Q-learning and understand how deep RL and RLHF build on it
Curriculum
Module 1 · Foundations
5 lectures- 01The agent–environment loop3D modelFree16 min
- 02Multi-armed bandits: explore or exploit?InteractiveFree17 min
- 03Markov decision processesInteractiveFree18 min
- 04Value functions and the Bellman equation3D modelFree19 min
- 05Q-learning: learning from experience3D modelFree21 min
Module 2 · Scaling up
5 lectures- 06SARSA and temporal-difference learningIncluded with the course
- 07Function approximation and deep Q-networksIncluded with the course
- 08Policy gradientsIncluded with the course
- 09Actor–critic methods and PPOIncluded with the course
- 10Exploration strategiesIncluded with the course
Module 3 · Reinforcement learning in the real world
4 lectures- 11Model-based RL and planningIncluded with the course
- 12Reinforcement learning from human feedbackIncluded with the course
- 13Offline RL and simulationIncluded with the course
- 14Safety, reward hacking and deploymentIncluded with the course
Who this course is for
- ML engineers exploring decision-making systems
- Engineers working on recommendation, pricing or control problems
- Anyone curious how RLHF shapes today’s AI assistants
Before you start
Basic probability and Python. Machine Learning Foundations is helpful but not required.
Keep going
Related courses
AI & Machine Learning
Machine Learning Foundations
Real intuition for how machines learn from data — models, loss, gradients and generalization.
5 free lectures$59₹3,999
AI & Machine Learning
Deep Learning
Neural networks from the ground up — neurons, backpropagation, optimizers and the techniques that make deep models train.
5 free lectures$79₹5,499
Training a team on this?
We can combine Reinforcement Learning with other courses into a learning path built around your team’s roles and goals.