Return to Question

A few improvements

Source Link

edited Feb 15, 2019 at 19:22

41.4k
12
114
205

What is the meaning of Model(s, a) in the prioritized sweeping in reinforcement leaninfalgorithm?

I have studiedI'm reading the reinforcement learning book by prof"Reinforcement Learning: An Introduction" (by Andrew Barto and Richard S. Sutton). He provided

The authors provide the pseudo codepseudocode of "the prioritized sweeping" algorithm, but I do not know what is the meaning of Model(s, a). Does it mean that Model(s,a) justModel(s, a) is the history of rewards gaindgained when we are in state s and actiothe action a is taken?

Does R, S_new = Model(s,a)

Does the above line mean that we should take a random sample from rewards gained in state s and action a is taken?

prioritized sweeping in reinforcement leaninf

I have studied the reinforcement learning book by prof. Sutton. He provided the pseudo code of "prioritized sweeping" algorithm but I do not know what is the meaning of Model(s,a). Does it mean that Model(s,a) just the history of rewards gaind when we are in state s and actio a is taken?

R,S_new = Model(s,a)

Does the above line mean that we should take a random sample from rewards gained in state s and action a is taken?

What is the meaning of Model(s, a) in the prioritized sweeping algorithm?

I'm reading the book "Reinforcement Learning: An Introduction" (by Andrew Barto and Richard S. Sutton).

The authors provide the pseudocode of the prioritized sweeping algorithm, but I do not know what is the meaning of Model(s, a). Does it mean that Model(s, a) is the history of rewards gained when we are in state s and the action a is taken?