Powered by AISKOOL
Reinforcement Learning in Python
Master reinforcement learning from the ground up — build intelligent agents that learn through trial and error using MDPs, Q-learning, policy gradients, and OpenAI Gym.
4 sections·14 lessons
What you'll learn
1. Foundations of Reinforcement Learning
- What Is Reinforcement Learning?
- The Agent-Environment Loop
- Markov Decision Processes (MDPs)
2. Q-Learning and Value-Based Methods
- Value Functions and the Bellman Equation
- Implementing Q-Learning from Scratch
- Q-Table Visualization
- OpenAI Gym: Your Training Ground
3. Policy Gradient Methods
- Why Policy Gradients?
- REINFORCE: The Vanilla Policy Gradient
- Policy Gradient Optimization Landscape
- Knowledge Check: RL Fundamentals
4. Training Agents and Going Deeper
- Deep Q-Networks (DQN)
- Proximal Policy Optimization (PPO)
- Building and Evaluating Your First Full Agent
Share this course