<< Chapter < Page Chapter >> Page >

And so you could actually choose 5-S equals S. That would be one reasonable choice, if you want to approximate the value function as a linear function of the states, but you can also choose other things, so for example, for the inverted pendulum example, you may choose 5-S to be equal to a vector of features that may be [inaudible]1 or you may have Xdot2, Xdot maybe some cross terms, maybe times X, maybe dot2 and so on. So you choose some vector or features and then approximate the value function as the value of the state as is equal to data transfers times the features. And I should apologize in advance; I’m overloading notation here. It’s unfortunate. I use data both to denote the angle of the cart of the pole inverted pendulum. So this is known as the angle T but also using T to denote the vector of parameters in my [inaudible]algorithm. So sorry about the overloading notation.

Just like we did in linear regression, my goal is to come up with a linear combination of the features that gives me a good approximation to the value function and this is completely analogous to when we said that in linear regression our estimate, my response there but Y as a linear function a feature is at the input. That’s what we have in linear regression. Let me just write down value iteration again and then I’ll written down an approximation to value iteration, so for discrete states, this is the idea behind value iteration and we said that V(s) will be updated as R(s) + G [inaudible].

That was value iteration and in the case of continuous states, this would be the replaced by an [inaudible], an [inaudible]over states rather via sum over states. Let me just write this as R(s) + G([inaudible]) and then that sum over T’s prime. That’s really an expectation with respect to random state as prime drawn from the state transition probabilities piece SA of V(s) prime. So this is a sum of all states S prime with the probability of going to S prime (value), so that’s really an expectation over the random state S prime flowing from PSA of that. And so what I’ll do now is write down an algorithm called fitted value iteration that’s in approximation to this but specifically for continuous states. I just wrote down the first two steps, and then I’ll continue on the next board, so the first step of the algorithm is we’ll sample. Choose some set of states at random. So sample S-1, S-2 through S-M randomly so choose a set of states randomly and initialize my parameter vector to be equal to zero. This is analogous to in value iteration where I might initialize the value function to be the function of all zeros. Then here’s the end view for the algorithm. Got quite a lot to write actually. Let’s see. And so that’s the algorithm. Let me just adjust the writing. Give me a second. Give me a minute to finish and then I’ll step through this. Actually, if some of my handwriting is eligible, let me know. So let me step through this and so briefly explain the rationale. So the hear of the algorithm is - let’s see. In the original value iteration algorithm, we would take the value for each state, V(s)I, and we will overwrite it with this expression here. In the original, this discrete value iteration algorithm was to V(s)I and we will set V(s)I to be equal to that, I think. Now we have in the continuous state case, we have an infinite continuous set of states and so you can’t discretely set the value of each of these to that. So what we’ll do instead is choose the parameters T so that V(s)I is as close as possible to this thing on the right hand side instead. And this is what YI turns out to be. So completely, what I’m going to do is I’m going to construct estimates of this term, and then I’m going to choose the parameters of my function approximator. I’m gonna choose my parameter as T, so that V(s)I is as close as possible to these. That’s what YI is, and specifically, what I’m going to do is I’ll choose parameters data to minimize the sum of square differences between T [inaudible]plus 5SI. This thing here is just V(s)I because I’m approximating V(s)I is a linear function of 5SI and so choose the parameters data to minimize the sum of square differences. So this is last step is basically the approximation version of value iteration. What everything else above was doing was just coming up with an approximation to this term, to this thing here and which I was calling YI. And so confluently, for every state SI we want to estimate what the thing on the right hand side is and but there’s an expectation here. There’s an expectation over a continuous set of states, may be a very high dimensional state so I can’t compute this expectation exactly. What I’ll do instead is I’ll use my simulator to sample a set of states from this distribution from this P substrip, SIA, from the state transition distribution of where I get to if I take the action A in the state as I, and then I’ll average over that sample of states to compute this expectation. And so stepping through the algorithm just says that for each state and for each action, I’m going to sample a set of states. This S prime 1 through S prime K from that state transition distribution, still using the model, and then I’ll set Q(a) to be equal to that average and so this is my estimate for R(s)I + G(this expected value for that specific action A). Then I’ll take the maximum of actions A and this gives me YI, and so YI is for S for that. And finally, I’ll run really run linear regression which is that last of the set [inaudible]to get V(s)I to be close to the YIs. And so this algorithm is called fitted value iteration and it actually often works quite well for continuous, for problems with anywhere from 6- to 10- to 20-dimensional state spaces if you can choose appropriate features. Can you raise a hand please if this algorithm makes sense? Some of you didn’t have your hands up. Are there questions for those, yeah?

Questions & Answers

A golfer on a fairway is 70 m away from the green, which sits below the level of the fairway by 20 m. If the golfer hits the ball at an angle of 40° with an initial speed of 20 m/s, how close to the green does she come?
Aislinn Reply
cm
tijani
what is titration
John Reply
what is physics
Siyaka Reply
A mouse of mass 200 g falls 100 m down a vertical mine shaft and lands at the bottom with a speed of 8.0 m/s. During its fall, how much work is done on the mouse by air resistance
Jude Reply
Can you compute that for me. Ty
Jude
what is the dimension formula of energy?
David Reply
what is viscosity?
David
what is inorganic
emma Reply
what is chemistry
Youesf Reply
what is inorganic
emma
Chemistry is a branch of science that deals with the study of matter,it composition,it structure and the changes it undergoes
Adjei
please, I'm a physics student and I need help in physics
Adjanou
chemistry could also be understood like the sexual attraction/repulsion of the male and female elements. the reaction varies depending on the energy differences of each given gender. + masculine -female.
Pedro
A ball is thrown straight up.it passes a 2.0m high window 7.50 m off the ground on it path up and takes 1.30 s to go past the window.what was the ball initial velocity
Krampah Reply
2. A sled plus passenger with total mass 50 kg is pulled 20 m across the snow (0.20) at constant velocity by a force directed 25° above the horizontal. Calculate (a) the work of the applied force, (b) the work of friction, and (c) the total work.
Sahid Reply
you have been hired as an espert witness in a court case involving an automobile accident. the accident involved car A of mass 1500kg which crashed into stationary car B of mass 1100kg. the driver of car A applied his brakes 15 m before he skidded and crashed into car B. after the collision, car A s
Samuel Reply
can someone explain to me, an ignorant high school student, why the trend of the graph doesn't follow the fact that the higher frequency a sound wave is, the more power it is, hence, making me think the phons output would follow this general trend?
Joseph Reply
Nevermind i just realied that the graph is the phons output for a person with normal hearing and not just the phons output of the sound waves power, I should read the entire thing next time
Joseph
Follow up question, does anyone know where I can find a graph that accuretly depicts the actual relative "power" output of sound over its frequency instead of just humans hearing
Joseph
"Generation of electrical energy from sound energy | IEEE Conference Publication | IEEE Xplore" ***ieeexplore.ieee.org/document/7150687?reload=true
Ryan
what's motion
Maurice Reply
what are the types of wave
Maurice
answer
Magreth
progressive wave
Magreth
hello friend how are you
Muhammad Reply
fine, how about you?
Mohammed
hi
Mujahid
A string is 3.00 m long with a mass of 5.00 g. The string is held taut with a tension of 500.00 N applied to the string. A pulse is sent down the string. How long does it take the pulse to travel the 3.00 m of the string?
yasuo Reply
Who can show me the full solution in this problem?
Reofrir Reply
Got questions? Join the online conversation and get instant answers!
Jobilize.com Reply

Get Jobilize Job Search Mobile App in your pocket Now!

Get it on Google Play Download on the App Store Now




Source:  OpenStax, Machine learning. OpenStax CNX. Oct 14, 2013 Download for free at http://cnx.org/content/col11500/1.4
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Machine learning' conversation and receive update notifications?

Ask