Reinforcement Learning Chapter 2: Multi-Armed Bandits

Показать описание

Thanks for watching this series going through the Introduction to Reinforcement Learning book! I think this is the best book for learning RL and hopefully these videos can help shed light on some of the topics as you read through it yourself!
Thanks for watching! Please Subscribe!

Рекомендации по теме

Комментарии

doing the Coursera course then review with this is nice!

minht.nguyen

These explanations are great. Thanks for making these videos!

Nakkers

two minutes in and the entire complex ball of RL seems much simpler. thank you. subbed

zakariaabderrahmanesadelao

I know you mention it at least once, but could you define the variables you use in the equations at least once on the slides? Would be quite helpful.

dipanshueminem

at 5:00, aren't you supposed to use n = 5, since we are calculating n = 6, which is n + 1. Therefore, should it not have been (12 - 8)/5 ?

kkyars

Hi, appreciate if anyone would share the link of policy gradient video mentioned in 11:49. Thanks.

vincentchong

At 4:02 how is the target 12? Like where does that value come from? Other than these videos are great, really saving me in my RL class

TheCreativeReilly

For absolute beginners, perfect at 0.75x speed.

TheDestint

At around 8:45 in the video, I think the action-value estimate should be initialized to 5 not the rewards.

jaym

at 6.16 I don't understand why the value change over time in greedy algorithm! even with small amount

shouldn't the value be the same because we don't discover at all which mean the same value repeated every timestep?

husamalsayed

Excellent, your speech is very clear, and I'm curious about the slides presentation software in your video, could you tell me what the app you use? I just want to try it~

chainszz

Is the greedy action selection rule also termed as 'best action in hindsight' ?

Aditya-nelk

Thanks a lot for making this series! could you send me the link for these slides?

maggs

This is exactly what I was looking for, thanks!

soareverix

Thanks a lot for such a good explanation and your time!

saberkazeminasab

thanks a lot for such wonderful explanations <3

mahimanzum

Reinforcement Learning Chapter 2: Multi-Armed Bandits

Reinforcement Learning Chapter 2: Multi-Armed Bandits

Multi-Armed Bandit : Data Science Concepts

Reinforcement Learning Chapter 2: Multi-Armed Bandits With Code

ECE493 - Week 2 - Part 1 - Multi-armed Bandits

RL Chapter 2 Part1 (Multi-armed bandits problems, epsilon-greedy policies)

Data Science in 30 Minutes #4: Reinforcement Learning and Multi-Armed Bandits

Reinforcement Learning Theory: Multi-armed bandits

Multi Armed Bandits - Reinforcement Learning Explained!

RL Chapter 2 Part2 (Multi-armed bandits: Recursive value estimates formulas, setting initial values)

Reinforcement Learning S & B: K-Armed Bandits

Multi-Armed Bandits: A Cartoon Introduction - DCBA #1

RL CH2 - Multi-Armed Bandit

The multi-armed bandit model in reinforcement learning

Multi-Armed Bandit Problem and Epsilon-Greedy Action Value Method in Python: Reinforcement Learning

Multi-armed bandit - Practical Reinforcement Learning

Reinforcement Learning: Multi-Armed Bandit example

Practical Reinforcement Learning - Multi-Armed Bandits (2.0)

Reinforcement Learning: Thompson Sampling & The Multi Armed Bandit Problem - Part 01

What are Multi-Armed Bandits ? #artificialintelligence #machinelearning #datascience

Multi-Armed Bandits Intro

Hands-On Reinforcement Learning with R | 4: Multi-Armed Bandit Models

Best Multi-Armed Bandit Strategy? (feat: UCB Method)

RL - Chapter 2: Multi-armed Bandits

K-Armed Bandit Problem - Part One