Markov Decision Processes 1 - Value Iteration | Stanford CS221: AI (Autumn 2019)
ฝัง
- เผยแพร่เมื่อ 4 มิ.ย. 2024
- For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: stanford.io/3pUNqG7
Topics: MDP1, Search review, Project
Percy Liang, Associate Professor & Dorsa Sadigh, Assistant Professor - Stanford University
onlinehub.stanford.edu/
Associate Professor Percy Liang
Associate Professor of Computer Science and Statistics (courtesy)
profiles.stanford.edu/percy-l...
Assistant Professor Dorsa Sadigh
Assistant Professor in the Computer Science Department & Electrical Engineering Department
profiles.stanford.edu/dorsa-s...
To follow along with the course schedule and syllabus, visit:
stanford-cs221.github.io/autu...
Chapters:
0:00 intro
2:12 Course Plan
3:45 Applications
10:48 Rewards
18:46 Markov Decision process
19:33 Transitions
20:45 Transportation Example
29:28 What is a Solution?
30:58 Roadmap
36:36 Evaluating a policy: volcano crossing
37:38 Discounting
53:21 Policy evaluation computation
55:23 Complexity
57:10 Summary so far
#artificialintelligencecourse
This lecturer is world class...and this is also the most confident live coding I have seen in a while...she is really really good. Universities are made by the lecturers...not so much the name
professor is so talented can’t say anything just feared over her, can’t take anymore
Thank you for this lecture and the course order. The past lectures about search problems really help you to better understand MDPs.
this was by far the most impressive lecture with live coding that I had seen! I am leaving this virtual lecture room with awe and respect...
I was lost on the MDP. Glad I find this awesome lecture clears all concepts in MDP! Very helpful!
thank you for posting this. MDPs were really confusing and this lecture really helped me understand it clearly.
Yes this is very very confusing topic
I wanna appreciate this lecture, its good. i had a difficult time and mental block for this topic. I wanna say thanks for all ur efforts.
It was my n-th iteration of MDP -where n>10 but using terminology of of MDP my knowlege finnally started to converge to proper direction. Thank you for the lecture🙂
this teacher is really really good. I wish you were at my Uni so that i could enjoy machine learning
Amazing lecture, loved every bit of it
This is an awesome lecture! Thank you so much.
Thank you professor! I learnt to much from this, especially the live coding bits.
Thanks for the awesome lecture. Very good job at explanation by the lecturer.
At 29:36, a policy is defined as a one-to-one mapping from the state space to the action space; for example, the policy when we are in station-4 is to walk. This definition is different compated to the one made in the classic RL book by Sutton and Barto; they define a policy as "a mapping from states to probabilities of selecting each possible action." For example, the policy when we are in station-4 is a 40% chance of walking and 60% chance of taking the train. The policy evaluation algorithm that is presented in this lecture also ends up being slightly different by not looping over the possible actions. It is nice of the instructor to highlight that point at 55:45
Action is determined from the beginning independent of states in this class...This will mislead beginners to confuse Q and V, as by this definition @47:20. In RL, we take action by policy, which is random and can be learned/optimized by iterating through episodes, i.e., parallel worlds.
Great Lecture, Thank you Professor :)
A thorough lecture!!
لذت بردم خانم صدیق. کیف کردم .. مممنووونننن
Thank you very much
This is really great lecture it's really helpful
Hi Ammar, glad it was helpful! Thanks for your feedback
Thank for amazing lecture!
Where are all the comments?
Thank you for your interesting lecture this lecture really helped me to understand it well.
Hi Alemayehu, thanks for your comment! Nice to hear you enjoyed this lecture.
@@stanfordonline Thanks for your reply. I am following you from Ethiopia and had interest on the subject area. Would you mind in suggesting best texts and supporting video's which may be helpful to have in-depth knowledge in the areas of Markov Processes and decision making specially related to manufacturing industries?
Thanks for the good lecture
would not removing constraint increase search space making computationally inefficent?
The transportation example has a problem. The states are discrete. If you take the tram, the starting state equals 1, and with state*2, you will never end up in state=3. Let's assume the first action was successful, therefore, the next state is 2. If the second action is successful too, you will be end up in state = 4. you will never end up in state = 3.
Great videos, thanks!. At time 47:20 on the board a small typo, I guess it should be: V_{\pi}(s) = Q_{\pi}(s, \pi(s)) if s not the end state.
FYI I'm a theoretical physics major, and I have no business in CS and whatsoever
Can in the Dice Game If choose to stay for the step 1 and then quit in the second stage: will I get 10 dollars if I choose to quit in the stage 2? Because If I am lucky enough to go to second stage i.e the dice doesn't roll 1,2 then I am in the "In" state and by the diagram I have option to quit which might give me 10 dollar but for that I should have success in stage 1. Then the best strategy might change. Let know what are your comments?
You are right according to the figure and flow of the states, but from the scenario ones get the perception that ones has a chance to either quit at the start or stay in the game.
Amazing lecture! I was having trouble finding my footing on this topic and now I feel I have a good starting point of the concepts and notations! I hope Professor Sadigh teaches many more AI topics!
Excellent, thanks for your feedback!
Mm
Mmmm
Pp
09
I will be conducting a test for those watching the video.
I think the given definition for value-action function (Q(s, action)) is not correct. In fact value function is the summation of value-action functions over all actions.
Wow this account crazy 😮
@47:20 the definition of Q function is not right and confuses with Value function. Specifically, take immediate reward R out of summation. The reason is Q function is to estimate the value of a specific Action beginning with current State.
or we may say the Value function here is not properly defined without considering policy, i.e., by taking action independent of states.
U should look at andrew ng's lecture, he explains it way better
Only watching for educational purposes
😂😂
Does anyone think she look like Zoe Kazan?
Is it me or she looks like callie torres from grays anatomy 🤔
Only watching for educational purposes.
yes me too
Me too
Me too
16:42 thumbnail
Beauty and brainy.
why is she so beautiful 😳😳
Why not?
i love you
Hell naw bruh
637
My man
Professor is quite cute ❤️
Cute lecture by cute lady
I'm Indian and belongs to Bihar State 🇮🇳🇮🇳