- decks
- flashcards
- learners
Decks in this class (11)
0 - Terminology & Definitions
Actions 1,
Actor critic 2,
Advantage function 3
68
cards
1 - Intro
Reinforcement learning is about h...,
The markov assumption assumes tha...,
What is the difference between st...
9
cards
2 - MDP Planning
What is policy iteration 1,
What is value iteration 2,
What does p s s a stand for 3
29
cards
3 - Multi-Armed Bandits
In multiarm bandits what is regre...,
What are we balancing in mab prob...,
How do we calculate reward for ma...
26
cards
4 - Dynamic Programming
Dynamic programming assumes ____ ...,
What is dynamic programming 2,
Name 4 basic steps to solve a dp ...
8
cards
5 - Monte Carlo
Monte carlo policy evaluation is ...,
Monte carlo assumes __________ on...,
V is ________ biased unbiased est...
6
cards
6 - TD Learning
0
cards
7 - Model Free Control
In your own words what is q s a 1,
Off policy learning can learn to ...,
What do the letters in sarsa stan...
5
cards
8 - Value Function Approximation
List a couple of advantages of va...,
Neural networks deep learning is ...,
Gradient descent is guaranteed to...
4
cards
9 - Deep RL
Deep neural networks dnn are func...,
The nonlinearity in a dnn is call...,
Why are convolutional neural netw...
9
cards
10 - Policy Optimization
Value function approximation vfa ...,
Policy search typically results i...,
In general one of the biggest rea...
11
cards
More about
Reinforcement Learning
- School Unspecified
- Program type Unspecified
- Course Unspecified
- Instructor Unspecified
- Standards Unspecified
The creator of this class did not yet add a description for what is included in this class.
How studying works.
Brainscape's adaptive web mobile flashcards system will drill you on your weaknesses, using a pattern guaranteed to help you learn more in less time.
Add your own flashcards.
Either request "Edit" access from the author, or make a copy of the class to edit as your own. And you can always create a totally new class of your own too!
What's Brainscape anyway?
Brainscape is a digital flashcards platform where you can find, create, share, and study any subject on the planet.
We use an adaptive study algorithm that is proven to help you learn faster and remember longer....
Looking for something else?
Reinforcement Learning
- 10 decks
- 143 flashcards
- 26 learners
Decks:
W1 Intro, W2 Mdp Tabular Value Based, W3 Deep Value Based, And more!
Bootcamp - Core Reinforcement I
- 29 decks
- 534 flashcards
- 25 learners
Decks:
Lesson 1 Bootcamp Core Reinforcement I, Lesson 2 Bootcamp Core Reinforcement I, Lesson 3 Bootcamp Core Reinforcement I, And more!
Learn Latin!
- 30 decks
- 2790 flashcards
- 111 learners
Decks:
Learn Latin Sampler, Vocab Enrichment 1, Vocab Enrichment 2, And more!
