Reinforcement Learning Tutorial | Reinforcement Learning Example Using Python | Edureka

🔥 Post Graduate Diploma in Artificial Intelligence by E&ICT Academy
NIT Warangal: www.edureka.co/executive-prog...
In this video on “Reinforcement Learning Tutorial” you will get an in-depth understanding about how reinforcement learning is used in the real world. I’ll be covering the following topics in this session:
(01:48) Introduction to Machine Learning
(05:51) What is Reinforcement Learning?
(06:55) Reinforcement Learning with an analogy
(07:54) Reinforcement Learning process
(08:57) Reinforcement Learning Counter-Strike example
(10:40) Reinforcement Learning Definitions
(13:01) Reinforcement Learning Concepts
(16:21) Markov’s Decision Process
(20:00) Understanding Q-Learning
(38:10) Demo
Check out our Python Training Playlist: goo.gl/Na1p9G
---------𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐏𝐲𝐭𝐡𝐨𝐧 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠𝐬----------
🔵Python Programming Certification: bit.ly/37rEsnA
🔵Python Certification Training for Data Science: bit.ly/2Gj6fux
---------𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐌𝐚𝐬𝐭𝐞𝐫𝐬 𝐏𝐫𝐨𝐠𝐫𝐚𝐦---------
🔵Data Scientist Masters Program: bit.ly/2t1snGM
🔵Machine Learning Engineer Masters Program: bit.ly/3Hi1sXN
----------𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐏𝐫𝐨𝐠𝐫𝐚𝐦---------
🌕Post Graduate Diploma in Artificial Intelligence Course offered by E&ICT Academy
NIT Warangal: bit.ly/3qdRRdw
How it Works?
1. This is a 5 Week Instructor led Online Course,40 hours of assignment and 20 hours of project work
2. We have a 24x7 One-on-One LIVE Technical Support to help you with any problems you might face or any clarifications you may require during the course.
3. At the end of the training you will be working on a real time project for which we will provide you a Grade and a Verifiable Certificate!
- - - - - - - - - - - - - - - - -
About the Course
Edureka’s Data Science Course on Python helps you gain expertise in various machine learning algorithms such as regression, clustering, decision trees, random forest, Naïve Bayes and Q-Learning. Throughout the Data Science Certification Course, you’ll be solving real life case studies on Media, Healthcare, Social Media, Aviation, HR.
During our Python Certification Training, our instructors will help you to:
1. Master the basic and advanced concepts of Python
2. Gain insight into the 'Roles' played by a Machine Learning Engineer
3. Automate data analysis using python
4. Gain expertise in machine learning using Python and build a Real Life Machine Learning application
5. Understand the supervised and unsupervised learning and concepts of Scikit-Learn
6. Explain Time Series and it’s related concepts
7. Perform Text Mining and Sentimental analysis
8. Gain expertise to handle business in future, living the present
9. Work on a Real Life Project on Big Data Analytics using Python and gain Hands on Project Experience
- - - - - - - - - - - - - - - - - - -
Why learn Python?
Programmers love Python because of how fast and easy it is to use. Python cuts development time in half with its simple to read syntax and easy compilation feature. Debugging your programs is a breeze in Python with its built in debugger. Using Python makes Programmers more productive and their programs ultimately better. Python continues to be a favorite option for data scientists who use it for building and using Machine learning applications and other scientific computations.
Python runs on Windows, Linux/Unix, Mac OS and has been ported to Java and .NET virtual machines. Python is free to use, even for the commercial products, because of its OSI-approved open source license.
Python has evolved as the most preferred Language for Data Analytics and the increasing search trends on python also indicates that Python is the next "Big Thing" and a must for Professionals in the Data Analytics domain.
For online Data Science training, please write back to us at [e-mail] or call us at IND: 9606058406 / US: 18338555775 (toll-free) for more information.

[@edurekaIN]

Got a question on the topic? Please share it in the comment section below and our experts will answer it for you. For Edureka Python Course curriculum, Visit our Website: bit.ly/2OpzQWw

[@wolfisraging]

That's why I love scratch implementation rather than using high end library, good job

[@wolfisraging]

Best tutorial for reinforcement learning, well done. Thank u so much

[@prasadgvs4639]

brilliant!! A perfect intro to ML. Well done Edureka!!

[@murtuza.chawala]

Edureka is the modern education system ! We love you, keep on the great work specially the free content !

[@rohitshaw3922]

it was really a great explanation . Thank you so much

[@ratangles820]

This is the most beautiful think Ive seen today :)

[@engineered.mechanized]

This was a great lecture.

[@fathialwosaibi4024]

Amazing video. Very well done, u managed to introduce a very technical matter into simple words. Tx for sharing

[@edurekaIN]

Thanks for the compliment, Fathi! We are glad you loved the video. Do subscribe to the channel and hit the bell icon to never miss an update from us in the future. Cheers!

[@systemsoftwareandcompilers3440]

Very well explained. Thank you very much

[@paichethan]

Nice explanation. Short , accurate and practical.

[@ipdevelopment1357]

What a fantastic video! Great work!!

[@rekhars1396]

Happy with the explanation. Thank you so much .😊

[@hidayatzeb1463]

I have never seen like this lecture in my entire life .expecting more video like this thank you

[@farenhite4329]

Amazing!! It’s so clear now!

[@bhargavamahesh]

Excellent and this is amazing to go through your video good job

[@hhhgdgb5205]

Thank you I like it, happy day .

[@ntsikelelonelsonmbekwa3231]

Wow :) Thanks edureka!

[@jim78able]

Very nicely explained, best tutorial ill show to my university also how edureka teaches

[@yunusemredarici7284]

ıt was so helpful . Thanks a lot:)

[@maheshvangala8472]

Good explanation thank you 😘

[@mattcoakes5682]

Very informative video,, thank you!

[@moriumakter9429]

good explanation. thank you

[@TheStrelok7]

You are legend!! Thank you!

[@adanesh]

what a simple and wonderful lecture

[@Asmutiwari]

well explained !! thanks

[@ranam]

Simple but powerful explanation

[@UlrichArmel]

Well done. I really understood this in 30 minutes after going through bunch of notes and maths without really understand what was happening. Thanks very much

[@edurekaIN]

Hey:) Thank you so much for your sweet words :) Really means a lot ! Glad to know that our content/courses is making you learn better :) Our team is striving hard to give the best content. Keep learning with us -Team Edureka :) Don't forget to like the video and share it with maximum people:) Do subscribe the channel:)

[@kanchan6731]

One of the bestest learning source I have ever seen 🙄

[@edurekaIN]

Thank you for appreciating our efforts, Kan. Do subscribe, like and share to stay connected with us. Cheers :)

[@bilalsadiq45]

This is one of the best lecture i have got to understand the crux of Q learning ,,hats off to you mam

[@edurekaIN]

Thanks for the compliment! We are glad we could help. Do subscribe to our channel to stay posted on upcoming tutorials.

[@anintrovert4128]

This video is better than Udacity nano degree ml program class on Reinforcement learning

[@guillaumenelson6996]

You explained it all in 46minutes. Thanks a lot!

[@edurekaIN]

You're welcome 😊 Stay connected with our channel and team :) . Do subscribe the channel for more updates : ) Hit the bell icon to never miss an update from our channel : )

[@guillaumenelson6996]

@@edurekaIN it was already done ✅ I did subscribe and hit the bell button 😊

[@syrymzhakypbekov1949]

I like it! Super! Keep Going!

[@ANIMESHKUMARPGP-]

Very good lecture, whoever was playing CS is a very good awper.....

[@spamspamer3679]

I really appreciated the explanation and that you didn't use any ML-libraries. But in my case, where you have two objects, which randomly spawn on a grid-map at the beginning of the "Game". One object (the "agent") has to reach the other object ("the goal"). But I can't create a matching matrix in this kind of problem, right? So, how should I deal with it?

[@edurekaIN]

Hey, Glad you liked the content. Your 'goal' is not an agent. It can't span around in the grid because the goal is fixed. Are you suggesting that you want to create two machine learning agents? Can you please be more specific about it.

[@rachanadesai7984]

very helpful!!

[@raginisharma9302]

Very Useful and easy to understand - brilliant teacher , thank you !!

[@edurekaIN]

Hi : ) We really are glad to hear this ! Truly feels good that our team is delivering and making your learning easier :) Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : ) Hit the bell icon to never miss an update from our channel : )

[@chintandd]

Wow. Nicely Explained by the instructor. I thought Python has inbuilt algo for calculating Q Matrix. But looking to the python code, I realized that we need to code it. Am I right?

[@edurekaIN]

Hi Chintan, thanks for watching the video. Yes, you need to write the code for Q Matrix.

[@kusumasriram2016]

Very clear explanation

[@santoshkumarsahu8482]

At Video 19:00 Policy {A->C->D) = 15+ 50 = 65 Policy (A->B->C->D} = 30 + (-10) + 50 = 70 IS IT CORRECT? Please Clarify....

[@anandsankar4014]

awesome explanation

[@muhammadusmanakram406]

excellent

[@dr.savitasheoran473]

very well explained

[@chaitanyakaushik6772]

Excellent explaination,really helpful..

[@edurekaIN]

Hi : ) We really are glad to hear this ! Truly feels good that our team is delivering and making your learning easier :) Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : ) Hit the bell icon to never miss an update from our channel : )

[@sgt.mcgragon359]

Halo, Great explanation but one doubt, I saw the code at the end.....are you using the same code to show the final Q matrix and path?.....because I am not getting the correct Q matrix and also the results are wrong!

[@edurekaIN]

Hey, The code creates and updates the Q matrix based on the movements of the agent. Can you please mention the error you are facing?

[@jeromystewart]

I liked the explanation and the flow of concepts but there are moments in this talk where the user (me/us) must ask, is the speaker instructing us based on an industry practice or on how this specific model is configured.. For example, when you say, the reward for an action that doesn't take you directly to the goal is zero .. do you mean that the goal is zero in this specific implementation or do you mean this is universally always that case. My brain gets hung up when the exact context isn't defined.

[@edurekaIN]

Hi Jeromy, thanks for watching the video. For each problem statement a different approach or a different model is built. So to answer your question, the instructor was referring to that particular problem statement. Hope this helps!

[@arnavverma8622]

Very good explanation

[@ragulsithuraj9929]

Hats off

[@venkystellar1877]

lucid explanation....I have a doubt....how can we decide the value of iterations?..the machine is intended to explore b those iterations?..

[@edurekaIN]

Hi Venky, thanks for the compliment! The iterations depends on the type of problem you're solving. Since this is a reinforcement learning problem, the agent requires more training because he must do everything from scratch.

[@Jeevankumar-ju2nt]

amazing session

[@sain5275]

Very well explained.. 👍

[@edurekaIN]

Glad you liked it

[@ymgindia]

Very good Explaination!..Thank You

[@edurekaIN]

We are super happy that Edureka is helping you learn better. Your support means a lot to us and it motivated us to create even better learning content and courses experience for you . Do subscribe the channel for more updates : ) Hit the bell icon to never miss an update from our channel : )

[@41abhishek]

Superb tutorial

[@sureshnambiar8566]

Excellent

[@Janani.G]

Fantastic

[@mergenlideki4055]

if there is a R(5,5) even though the end goal (room 5) is already reached, why is there no R(4,4), R(3,3), R(2,2) and R(1,1) ?

[@edurekaIN]

Hey, There is a (1,1), (2,2), (3,3), (4,4), connectivity, but the reward to traverse from node 4 to 4 is zero. Because node 1,2,3,4 are not the goal nodes. Hope this helps. Cheers!

[@raedm9244]

That was very good video. I am still learning. Thank You.

[@jitendravasava4586]

Present sir :)

[@mdmamun-vp9xj]

please make a video of kalman filter with python.

[@edurekaIN]

Hi Mamun, thank you for your suggestion. We will definitely come up with an exclusive tutorial for the same. Meanwhile, do subscribe to our channel and stay tuned. Cheers :)

[@surbhigupta1419]

nice video

[@akshaybhosale1100]

Nicely explained. But still I am getting an error in the code. Please guide me.

[@edurekaIN]

Hi Akshay, we regret the error in your code. However, you can drop your email id in the comments and we shall assist you with the source codes. Hope this might be helpful, cheers :)

[@rifanaaa2692]

What is the applications of reinforcement learning??

[@edurekaIN]

Here are some of the applications of Reinforcement Learning: 1. Robotics for industrial automation. 2. Business strategy planning. 3. Machine learning and data processing. 4. It helps you to create training systems that provide custom instruction and materials according to the requirement of students. 5. Aircraft control and robot motion control.

[@liaastuti1170]

sorry, how i get the code?

[@edurekaIN]

Hi Lia, kindly drop in your respective email id and we will share the code to you :)

[@Joseroberto-rr2wp]

Why the reward from minute 33.41 from Q(5,5) is not 100?

[@edurekaIN]

Hi Jose, Q(5,5) is zero initially because it represents the memory of the agent. On the other hand R(5,5) is 100 because it represents the reward the agent recieves on reaching the goal state (5).

[@ankitbrijwasi9902]

@@edurekaIN okay, thank you

[@annanyamathur8869]

please share code

[@edurekaIN]

Good to know our contents and videos are helping you learn better . We are glad to have you with us ! Please share your mail id to send the data sheets to help you learn better :) Do subscribe the channel for more updates : ) Hit the bell icon to never miss an update from our channel : )