hello,i'm trying to use PPO and A2C for my discrete-box environment. i have set negative rewards in order to teach the agent to avoid impossible operation in my environment. most of the training time is spent to learn to avoid those operations with negative rewards. Is there a method to directly "tell" the agent (inside the agent itself) to avoid those operations, instead of spend training time? thanks in advance

❤

❤

WTF MAN WHY DID I STUDY VERTEXES AND JOINTS AND ALL THAT STUFF?!

Hey man looks like the command "py -3.7" is not working for me. I doo have python 3.12 installed and when I check the list of environments it shows 3.12 and 3.8. How can I add 3.7 here. Should I go and add it in the env path and downloading python 3.7?

Is Sentdex the best Python coder in the world?

4 years later and still one of the best series on the subject

Thankyou bro❤

Get an error string indices must be integers, not 'str'

Can anyone access his python shell scripts? I'm having trouble with the input at the attribute category_slug. Were we not supposed to fill that attribute at the python shell. I feel lost

❤

why is this resource being underrated, people nowadays import tensorflow, and PyTorch, -> say u build a neural network, but this man combined theory and lab in such a way that it is easy to understand

"You won't get through this in a weekend" Challenge accepted.

Loved the videos, really helped me understand Neural Networks deeper. I’m looking forward to buying the book but I also enjoy the videos that you do. Are you going to continue video support for this series or is the book my only way forward from here?

for row in range(len(game)): diag1.append(game[row][row]) diag2.append(game[row][len(game)-1-row])

Your videos always feel so grounded. Most other videos on such topics make me feel so insignificant. Also, I have a friend, Zeke, from Florida, and you two are soo uncannily similar!!!!

That ain't a home lab it feels like a tiny datacenter

Epic video! :)

Still here ... still waiting ... with my book and my unwavering Will to wait

this is going over my head now

Brain is glitching

Can I Also try this on Pycharm IDE? Or do I Really need to Install SUblime?

I just purchased your book! You are too kind

Does anybody know about that copilot he used to speed up the decompressing process?

hi

bless you!

Love your website. Thank you.

Nice video

am literally doing this just to communicate with my girl😭😭😭😭

what the heck was that 35.7

❤

For people getting error while loading the saved model, use the activation functions of keras, not of tensorflow and specify input_shape of the first layer. Following are the code changes - from keras import activations model = tf.keras.models.Sequential() model.add(tf.keras.layers.Flatten(input_shape=(28,28))) model.add(tf.keras.layers.Dense(128, activation=activations.relu)) model.add(tf.keras.layers.Dense(128, activation=activations.relu)) model.add(tf.keras.layers.Dense(10, activation=activations.softmax))

This is a good course, but may I make a friendly positive comment.You need to separate out the discursive 'chat' from the Really Important Stuff. The RIS needs to be taken a little slower, and a little more carefully and with a slightly greater focus. And make sure all your code is visible on the screen.

❤

❤

❤

❤

I didn't understand why you put last 5 percent for index

I think one big issue with the model not working well, may be because of the traction and handling of the vehicle? Playing around with the vehicle using custom controls, I saw some serious handling and traction issues at high speeds, whereas vehicles like ambulances were handling really well in comparison. Just my two cents.

What do i do if the transposition of the weights isnt either the right shape not sure if this question makes sense i thought youd use a for loop and then make a output of the dot product for each input node for each output node

Shout out daniel

I think now would be a perfect time for a part 4 😁

Jesse Pinkman if he did math instead of meth

pls continue

wow nice tactic, just stop halfway and go quiet. what you want us to buy the book? no way dude. not supporting you.

love this tutorial and i followed it religiously but he said first-ith and i cried because i watched that part so much

Elon watched this and was like, X is the name of training data. Twitter data is training data. Twitter is X;

Wo what I am 8 years late

Thanks sentdex. Love the videos!

can you make a video about gradient decent optimization and backpropagation and their implemetations?