Presentation, Notes, and Codes are available at the following link: drive.google.com/drive/u/1/folders/1GiXH6e8rC0qCZ0c5ATiiRkXBdtBuBZGj
@SRINIVASANNR-t3mАй бұрын
Hello Rohan, I had cleared the exam with elite silver.The way you explained confusion matrix and probability is very good. Thanks a lot
@sunaasthaАй бұрын
Reinforcement Learning - ML feedback-based approach where agent learns to make decision by interacting with environment thru Trial and error process. Example: Dog fetching a Ball Agent: Dog Action (it takes) : Pick Ball Reward: Positive feedback, treats, praise etc. If not pick ball, no reward (ie. punishment). Therefore, Dog overtime learns thru trial-error and aims to maximize rewards.
@HimashwethaA.U3 ай бұрын
Helpful video
@rohanraha21572 ай бұрын
Thanks!
@Sanvitha20193 ай бұрын
Excellent Jii
@atishsinhaa3 ай бұрын
Some of the terminology i couldn't be able to understand in lectures provided
@rohanraha21573 ай бұрын
which terminologies?
@atishsinhaa3 ай бұрын
Bhaiya u are writing too small in this session please increase the font if possible from next time plz
@rohanraha21573 ай бұрын
Sure, will do
@Sanvitha20192 ай бұрын
Needs clear explanation
@pratikingle39633 ай бұрын
r u a student???
@rohanraha21573 ай бұрын
Yes
@AkhilRawat-ki8zk2 ай бұрын
You explained that so clearly , it really helped me grasp the concept. I would really appreciate connecting with you on LinkedIn.