Teach agents to learn from reward. Markov decision processes, Q-learning, and where reinforcement learning fits in the ML landscape.
BeginnerAbout 3 hours9 lessons
What you will learn
Agents, environments, and rewards
The reinforcement learning loop
Exploration vs exploitation
Markov decision processes
Q-learning and the Q-table
Hands-on: a Q-learning agent
From Q-tables to Deep Q-Networks
When to use reinforcement learning
Curriculum
1
Foundations of RL
3 lessonsFree preview
Agents, environments, and rewardsPreview8m
The reinforcement learning loopPreview7m
Exploration vs exploitationPreview7m
2
Value-based methods
3 lessons
Markov decision processes9m
Q-learning and the Q-table10m
Hands-on: a Q-learning agent10m
3
Going deeper
2 lessons
From Q-tables to Deep Q-Networks9m
When to use reinforcement learning7m
4
Hands-on checkpoint
1 lessons
Checkpoint: train an agent on a simple environment15m
Hands-on checkpoint
Every course ends with a Colab task you complete yourself. Our Gemini-assisted review gives feedback and points you to what to fix, it coaches you, it does not do it for you.