วีดีโอ

in my calculation s3 should be 0.9 , since Q(s3 ,a)=0+0.9×max(0,1,0) from here s2 =0.81 s1 = 0.729 , .....

Do you mean that we can use recursive approach (dynamic programming) to find value of all states. Or We can find value of all states by iteration

thank you for explanation

dude thank you your videos are awesome

The past doesn’t matter baby!!!!!

Thanks You Skowster

One of the most underated video on MDP I have seen

What happens if instead of mario being drunk we had that Mario can move how instructed but the identity of the two rooms trap and success are unknown, but information is known of the probability that either is trap or success. i.e. mario knows that the success room may be trap with 50 % confidence

Thank you for making this, very helpful.

The link to the "free Move 37 Reinforcement Learning course" mentioned in the description appears to be dead.

Great presentation- thank you

Awesome explanation.

This explanation helps me a lot! Thank you!

Hi mate, thanks for 3 amazing videos on AlphaGo Zero. Where can I find part 4?

Thank you for this

Thanks Skowster, you're a real one!

Thank you for this concise video. The texts provided by my lecturer wasn't this easy to understand

This guy took this complicated formula and made it easy

So clear, thank you!

I got quickly hooked by the first video on bellman equation as it was simple, intelligent and lucid and immediately watched this one. Alas, quickly lost interest on this one as it starts with some lame gimmicks and I am no longer sure what to expect. You could have followed the simple style of the first one and got another million views..Will look for other material. Thanks

sir, can you share any book name or any resources link or something to get more knowledge about continuous action space RL concepts. Please,please

Thanks a lot!!! This video is a true masterpiece. Got a lot of learning "clicks" out of it.

thumbs up for the quake reference :)

Fascinating

21.11 20:55

thank you very much sir 😍

The tutorial is for a stochastic policy or continuous action spaces?

Hi! It's a nice video. I wonder if I have continuous action values ranging from 50 to 150, which activation function should I use in the output Actor-network, and how to sample between those values from its probability?

Nice RL Playlist, thank you!

That means each action of the agent will give him a reward and if he finds the path or get to the goal then he will get maximum reward. But does an agent trys to find different ways to reach goals. Also i subscribed.

Great explanation, thank you! For me, the most confusing thing with PPO was what is the new policy vs the old policy (for the calculation of the ratio in the loss function) and how are gradients calculated when there are "two" policies. For some reason this is very often quickly glossed over, but it's pretty clear once you see the implementation. For anyone who was confused like I was, here's how I understand it. The old policy is the policy you use to choose actions - you calculate all the old_policy values during the environment sampling phase. These are numerical values which don't need to contribute directly to the gradients, so consider them scalars. Then you do several epochs of updates to the model: On epoch 0 new_policy = old_policy and therefore the ratio is always 1 and the loss is actually just the advantage function (and no clipping obviously) On the next epoch, you made an update to the model, which is now considered the new policy; but the old policy is still the same (already calculated). Therefore, the ratio may now differ from 1 and you make an update according to the loss formula (clipping and all)

Thank you for the nice explanations and video. It is useful. I hope your videos about ML&Data Science will continue.

The first time I a have a feeling of what Bellman’s equation is for. Awesome video.

A very positive start of the video thanks you, keep going and we keep supporting

Simple and clear❤️

I am working on machine learning and this was new to me. Thanks for bringing it to my attention.

Brilliantly explained 👍🏼👍🏼

10:45. I think you might have some error here. The equation is V(s) = max(R(s,a) + r*V(s')) i.e. V(s) max of the sum of the reward of the CURRENT cell (which is s) plus the V-value of its best NEIGHBOUR (which is s'). so the V-value of the cell left of the princess should be V = 0 + 0.9 * 1 = 0.9, not 1, right?

you make me god ty.

There are too many videos focusing on explaining theory and equations which are easy to research as there is plenty of theoretical knowledge helping to work out all the math beyond the equations. Although, there are too few good quality videos focused on practice and coding. Your video is an outstanding one!

good one, ty!

11:42 you lost me there You said the state of the next square is 0 that's why it's 0 + but then you go ahead and say the value of the square is 1. are the state and value of the square different? I thought the state was the square?

you're a crack, i love it! cool video!!!

Is AC still the leading algorithm for tasks such as self-driving?

This is greate tutorial. Thanks for the talk.

subscribed :)

You're so funny! 🤓

What is a prime state, is the max V(s) at state, or ?

thanks alot mannnnnnn

3:44 It's fascinating to note that in 1954 there were no digital computers. I wonder if they were using analog computers.