The libraryrl · advanced

Reinforcement Learning

MDPs, Q-learning, policy gradients, PPO, and deep RL. Train agents that learn from interaction.

· 1 learners
35 hours · 34 lessons
01What you'll build · week by week
34 lessons total
From the reviews
“Closer to an apprenticeship than a course.”
Marco V. · Engineer · Linear
What you'll have shipped
01A working rl project
02Reviewed code, retired and promoted
03A portfolio piece you'd actually link to