Back to Courses

Reinforcement Learning

Advanced 4.7 (1.2k reviews)

Train agents to make decisions. From Q-Learning to Deep Q-Networks and Policy Gradients.

Reinforcement Learning
Best Seller

Course Roadmap

Step 1

RL Foundations

Agents, Environments, States, Actions, and Rewards

Step 2

Markov Decision Processes

Bellman Equations and Value Functions

Step 3

Tabular Methods

Q-Learning and SARSA

Step 4

Deep Q-Networks (DQN)

Experience Replay and Target Networks

Step 5

Policy Gradients

REINFORCE Algorithm and Actor-Critic Methods

Step 6

PPO & TRPO

Proximal Policy Optimization for Stable Training

Step 7

Multi-Agent RL

Cooperative and Competitive Environments

Step 8

Capstone

Train a Robot to Navigate a Maze