AML Reinforcement Learning Flashcards

1
Q

What is the 7-letter mnemonic for the key components of RL?

A

APO.DARO

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the 6 key components of reinforcement learning?

A

an Agent functions with a Policy, makes Observations, leading to Decisions, that output Actions, that result in Rewards or more observations.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the first step in RL for a data scientist?

A

Develop the training script.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is Q-Learning?

A

One of the earliest RL algorithms.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is PPO?

A

Proximal Policy Optimisation

A RL algorithm approach.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Name the points on the diagram

A

See unmasked image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly