![Alborz Geramifard](/img/default-banner.jpg)
- Видео 2
- Просмотров 20 761
Alborz Geramifard
Добавлен 6 авг 2013
An Introduction to Markov Decision Processes and Reinforcement Learning
RLPy: rlpy.readthedocs.io/en/latest/
AI Gym: gym.openai.com/
Tutorial Paper: A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning (alborz-geramifard.com/Files/13FTML-RLTutorial.pdf)
AI Gym: gym.openai.com/
Tutorial Paper: A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning (alborz-geramifard.com/Files/13FTML-RLTutorial.pdf)
Просмотров: 19 009
Видео
MovieBot
Просмотров 1,8 тыс.7 лет назад
* The thinking time on my side and Echo's side were clipped out. The thinking time on Echo's side is peaked around couple of seconds. * MovieBot is available to public as an Alexa skill. Just say "Alexa, enable moviebot" and then "Alexa, open moviebot" * We are working on more features and would love to hear suggestions/comments. * MovieBot was developed using Alexa ASK: developer.amazon.com/al...
amazing
The best video on this topic. Thanks a lot!
there are obvious cuts between questions and answers 😂😂😂😂 this should be really embarrassing 😂😂😂
15:47 I'm intrigued by the mathematical symbols. I've never seen an upside down "A" before. It's assumed we know these symbols. I've taken calculus, trig, etc, but I don't have familiarity with all of the these symbols.
The "upside down 'A' " means "for all." It is commonly used in proof-based math courses.
In the part of value iteration example, I don't understand when he say that transition model is valid for every direction. So total transition probability is 4 but not to be 1. Can someone help me to explain it?
This is absolutely one of the best presantation I have ever seen about the introductory RL on internet. I don't understand why this is not watched that much! Could you please share a video about the MC methods and Policy Gradients methods (A2C,DDPG etc.) in RL as well? I really like the way you teach! Thanks a lot for this video!
Thanks alot Professor Really a great lecture !
the Q&A goes on for far too long. better to leave the such repeated questions till the end.
آقا دم شما گرم، عالی بود، میشه خواهش کنم اگر ویدیویی بابت MARL داشتید آپلود بفرمایید؟
Interesting response to the ambiguous "rating" question. How would you ask to get the other type of rating - "movie rating", "MPAA rating"?
What is the formula for calculating upper bound of MDP?
nice conversation. Though it would be better if there was no cut before each answer by Alexa
I tried it. This is super cool! Great work, Alborz!
Awesome job!