RL2 Flashcards by Alessandro Viespoli

Q

Backward view TD(lamba) - pseudo

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

Sarsa(lamba) - pseudo

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

Gradient MC for estimating v_hat

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

Semi-gradient TD(0) for estimating v_hat

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

Semi-gradient n-step for estimating v_hat

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

Episodic semi-gradient Sarsa for stimating q_hat

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

MC policy gradient method for estimating pi_theta

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

QAC

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly

Q

QAC with advantage function

A

How well did you know this?

1

Not at all

2

3

4

5

Perfectly