In this Julia coding tutorial, you'll get a gentle introduction to Reinforcement Learning by learning about the Markov Decision Process using the POMDPs.jl package.
You'll learn how to construct an MDP, which is like an artificial world where you can insert an Intelligent Agent.
After constructing the MDP, you'll learn how to solve it by using the Value Iteration Algorithm.
The result will be something called a "Policy" which is like a treasure map from your Intelligent Agent.
- This tutorial is intended for students, hobbyists and amateurs.
- This tutorial is episode 12 of a 13-part series and is part of the Julia Machine Learning for Beginners playlist.
- Schedule: New tutorials are posted on Sundays / Mondays.
- Prerequisites: Julia, VS Code and Episodes 501 through 511.
00:00 Intro
00:54 Reinforcement Learning
02:19 Markov Decision Process (MDP)
07:17 POMDPs.jl Package
10:11 Set Up
12:07 GridWorld (motivating example)
28:19 Recap
29:54 Outro
########################################
Links for this tutorial
########################################
Code for this tutorial:
github.com/julia4ta/tutorials...
Link to POMDPs.jl (GitHub)
github.com/JuliaPOMDP/POMDPs.jl
Link to POMDPs.jl (documentation)
juliapomdp.github.io/POMDPs.j...
Link to POMDPModelTools.jl (GitHub)
github.com/JuliaPOMDP/POMDPMo...
Link to QuickPOMDPs (GitHub)
github.com/JuliaPOMDP/QuickPO...
Link to DiscreteValueIteration.jl (GitHub)
github.com/JuliaPOMDP/Discret...
Link to JuliaPOMDP Repository (GitHub)
github.com/JuliaPOMDP
########################################
Links for additional resources
########################################
Link to "Decision Making Under Uncertainty using POMDPs.jl" Playlist (KZfaq)
• Introduction to Decisi...
Link to JuliaCon 2017 | Decision Making under Uncertainty | Mykel Kochenderfer (KZfaq)
• Decision Making under ...
Link to Algorithms for Decision Making, Kochenderfer, Wheeler, & Wray
algorithmsbook.com/
Link to Reinforcement Learning: An Introduction, Sutton & Barto
incompleteideas.net/book/the-b...
Link to POMDPs.jl: A Framework for Sequential Decision Making under Uncertainty, Egorov, Sunberg, et al., Journal of Machine Learning Research, 2017
www.jmlr.org/papers/volume18/...
Link to Stanford Intelligent Systems Laboratory (SISL)
web.stanford.edu/group/sisl/c...
########################################
Links for this series
########################################
Link to Series 5 Playlist [Julia Machine Learning for Beginners]
• [05x01] What is Machin...
Andrew Ng's Stanford Machine Learning Course
Stanford CS229: Machine Learning | Autumn 2018
• Stanford CS229: Machin...
The Julia Programming Language
julialang.org/
docs.julialang.org/en/v1/
/ thejulialanguage
VS Code
code.visualstudio.com/
########################################
Notice of Non-Affiliation and Disclaimer:
I am not affiliated, associated, authorized, endorsed by, or in any way officially connected with Andrew Ng or Stanford University.
Nor am I affiliated, associated, authorized, endorsed by, or in any way officially connected with The Julia Programming Language, Julia Academy, Julia Computing, Microsoft, or any of their subsidiaries or their affiliates.
Nor am I affiliated, associated, authorized, endorsed by, or in any way officially connected with any software, packages or libraries used in this video.
All marks, emblems and images are registered trademarks of their respective owners. Use of them does not imply any affiliation with or endorsement by them.
########################################
Join Button (Channel Membership):
If you like what I do, then please consider Joining and becoming a Channel Member.
/ @doggodotjl
Thank you!