Curriculum
Course:
Reinforcement Learning Foundation
Login
Curriculum
Reinforcement Learning Foundation
Section 1: Introduction مقدمة
0/9
RLF_S1L1: When You Can't Write the Rules — Introduction to RL - مقدمة التعليم المعزز
12m
Preview
RLF_S1L1: Quiz 1
4 questions
RLF_S1L2: The 8 Words That Unlock Everything — Core Vocabulary
11.5m
Preview
RLF_S1L2: Quiz 2
4 questions
RLF_S1L3: Your Roadmap — Course Overview & Structure
9m
Preview
RLF_S1L4: From Zero to First Agent — Setup & Your First Code
9m
Preview
RLF_S1Code
17m
Preview
RLF_S1A: Section 01 Capstone — GridWorld Navigation Agent
Assignment
RLF_S1 Code
Text lesson
Section 2: Markov Decision Processes & Dynamic Programming
0/15
RLF_S2L1: The Markov Property & MDPs — The Universal RL Grammar
14m
Preview
RLF_S2L1: Quiz 3
4 questions
RLF_S2L2: The Bellman Equation & Value Functions (V and Q)
6m
RLF_S2L2: Quiz 4
9 questions
RLF_S2L3a: Value Iteration & Policy Iteration — The Two Dynamic Programming Roads
21m
Value Iteration Walkthrough
15 Min
Preview
RLF_S2L3b: Value Iteration & Policy Iteration — The Two Dynamic Programming Roads
16m
Policy Iteration Walkthrough
PDF lesson
RLF_S2L3:Quiz 5
4 questions
RLF_S2L4: Your First Solver — GridWorld in 30 Lines + Why It Converges
7m
RLF_S2L4: Quiz 6
4 questions
RLF_S2L5: Where DP Hits a Wall — The Curse of Dimensionality
8m
RLF_S2L5: Quiz 7
4 questions
RLF_S2 Code Lab
14m
Section 02 Capstone — Solve a Custom GridWorld with DP
Assignment
Section 3: Model-Free RL & Monte Carlo Methods
0/12
RLF_S3L1: When the Map Runs Out — Why Model-Free RL?
8m
RLF_S3L1: Quiz 8
5 questions
RLF_S3L2: MC Prediction — Two Ways to Count a Visit
6m
RLF_S3L2: Quiz 9
5 questions
RLF_S3L3: MC Control — From Prediction to Optimal Policies (ε-Greedy GPI)
18m
RLF_S3L3: Monte Carlo Control A Step-by-Step Walkthrough PDF
PDF lesson
RLF_S3L3: Quiz 10
5 questions
RLF_S3L4: Off-Policy MC & Importance Sampling
14m
RLF_S3L4: Off-Policy Monte Carlo One Dataset, Multiple Policy Evaluations PDF
PDF lesson
RLF_S3L4: Quiz 11
5 questions
RLF_S3L5: Solve Blackjack with First-Visit MC Control
5m
Build a Model-Free Blackjack Agent and Compare On-Policy vs Off-Policy MC
Assignment
Section 4: Temporal Difference Learning, SARSA & Eligibility Traces
0/20
RLF_S4L1: TD(0) — One-Step Temporal Difference
17m
RLF_S4L1: Walkthrough: TD(0) on a 3-State Random Walk PDF
PDF lesson
RLF_S4L1: Quiz 12
5 questions
RLF_S4L2: Eligibility Traces & the Forward/Backward View
16m
RLF_S4L2: Quiz 13
5 questions
RLF_S4L3: TD(n) — Multi-Step Returns
8m
RLF_S4L3: Walkthrough: n-Step TD on a 5-State Chain PDF
PDF lesson
RLF_S4L3: Quiz 14
5 questions
RLF_S4L4: Bias vs Variance — Why n Matters
7m
RLF_S4L4: Quiz 15
5 questions
RLF_S4L5: TD(λ) — Unifying the Spectrum
8m
RLF_S4L5: Walkthrough: TD(λ) — Computing the λ-Return PDF
PDF lesson
RLF_S4L5: Quiz 16
5 questions
RLF_S4L6: SARSA & SARSA(λ) — TD Control
6m
RLF_S4L6a: Walkthrough: SARSA on a 2-State, 2-Action Grid PDF
PDF lesson
RLF_S4L6b: Walkthrough: SARSA(λ) — Eligibility Traces in Action PDF
PDF lesson
RLF_S4L6: Quiz 17
5 questions
RLF_S4L7: Foundation Wrap-Up + What's Next
7m
RLF_S4L7: Quiz 18
5 questions
TD(0), n-Step TD, and SARSA(λ) on FrozenLake & CliffWalking
Assignment
Video lesson
RLF_S1Code
Lesson video progress:
0%
of
100%
Lesson Materials
S1_Coding_Lab_GridWorld.ipynb.txt
22 kb
Download
Sign In
Google
Facebook
Google
Facebook
or sign in with email
The password must have a minimum of 8 characters of numbers and letters, contain at least 1 capital letter
I want to sign up as instructor
Remember me
Sign In
Sign Up
Restore password
Send reset link
Password reset link sent
to your email
Close
Your application is sent
We'll send you an email as soon as your application is approved.
Go to Profile
No account?
Sign Up
Sign In
Lost Password?