# 2.12 Machine learning lecture 12 course notes  (Page 5/8)

 Page 5 / 8

can make it run much more quickly. Specifically, in the inner loop of the algorithm where we apply value iteration, if instead of initializing valueiteration with $V=0$ , we initialize it with the solution found during the previous iteration of our algorithm, then that will provide value iteration witha much better initial starting point and make it converge more quickly.

## Continuous state mdps

So far, we've focused our attention on MDPs with a finite number of states. We now discuss algorithms for MDPs that may have an infinite number of states. For example, for a car,we might represent the state as $\left(x,y,\theta ,\stackrel{˙}{x},\stackrel{˙}{y},\stackrel{˙}{\theta }\right)$ , comprising its position $\left(x,y\right)$ ; orientation $\theta$ ; velocity in the $x$ and $y$ directions $\stackrel{˙}{x}$ and $\stackrel{˙}{y}$ ; and angular velocity $\stackrel{˙}{\theta }$ . Hence, $S={\mathbb{R}}^{6}$ is an infinite set of states, because there is an infinite number of possible positionsand orientations for the car. Technically, $\theta$ is an orientation and so the range of $\theta$ is better written $\theta \in \left[-\pi ,\pi \right)$ than $\theta \in \mathbb{R}$ ; but for our purposes, this distinction is not important. Similarly, the inverted pendulum you saw in PS4 has states $\left(x,\theta ,\stackrel{˙}{x},\stackrel{˙}{\theta }\right)$ , where $\theta$ is the angle of the pole. And, a helicopter flying in 3d space has states of the form $\left(x,y,z,\phi ,\theta ,\psi ,\stackrel{˙}{x},\stackrel{˙}{y},\stackrel{˙}{z},\stackrel{˙}{\phi },\stackrel{˙}{\theta },\stackrel{˙}{\psi }\right)$ , where here the roll $\phi$ , pitch $\theta$ , and yaw $\psi$ angles specify the 3d orientation of the helicopter.

In this section, we will consider settings where the state space is $S={\mathbb{R}}^{n}$ , and describe ways for solving such MDPs.

## Discretization

Perhaps the simplest way to solve a continuous-state MDP is to discretize thestate space, and then to use an algorithm like value iteration or policy iteration, as described previously.

For example, if we have 2d states $\left({s}_{1},{s}_{2}\right)$ , we can use a grid to discretize the state space:

Here, each grid cell represents a separate discrete state $\overline{s}$ . We can then approximate the continuous-state MDP via a discrete-state one $\left(\overline{S},A,\left\{{P}_{\overline{s}a}\right\},\gamma ,R\right)$ , where $\overline{S}$ is the set of discrete states, $\left\{{P}_{\overline{s}a}\right\}$ are our state transition probabilities over the discrete states, and so on. We can then use value iteration or policy iterationto solve for the ${V}^{*}\left(\overline{s}\right)$ and ${\pi }^{*}\left(\overline{s}\right)$ in the discrete state MDP $\left(\overline{S},A,\left\{{P}_{\overline{s}a}\right\},\gamma ,R\right)$ . When our actual system is in some continuous-valued state $s\in S$ and we need to pick an action to execute, we compute the corresponding discretized state $\overline{s}$ , and execute action ${\pi }^{*}\left(\overline{s}\right)$ .

two downsides. First, it uses a fairly naive representation for ${V}^{*}$ (and ${\pi }^{*}$ ). Specifically, it assumes that the value function is takes a constant value over each of the discretization intervals(i.e., that the value function is piecewise constant in each of the gridcells).

To better understand the limitations of such a representation, consider a supervised learning problem of fitting a function to this dataset:

Clearly, linear regression would do fine on this problem. However, if we instead discretize the $x$ -axis, and then use a representation that is piecewise constant in eachof the discretization intervals, then our fit to the data would look like this:

This piecewise constant representation just isn't a good representation for many smooth functions. It results in little smoothing over the inputs, and nogeneralization over the different grid cells. Using this sort of representation, we would also need a very fine discretization (very small grid cells) to get a good approximation.

Preparation and Applications of Nanomaterial for Drug Delivery
Application of nanotechnology in medicine
what is variations in raman spectra for nanomaterials
I only see partial conversation and what's the question here!
what about nanotechnology for water purification
please someone correct me if I'm wrong but I think one can use nanoparticles, specially silver nanoparticles for water treatment.
Damian
yes that's correct
Professor
I think
Professor
what is the stm
is there industrial application of fullrenes. What is the method to prepare fullrene on large scale.?
Rafiq
industrial application...? mmm I think on the medical side as drug carrier, but you should go deeper on your research, I may be wrong
Damian
How we are making nano material?
what is a peer
What is meant by 'nano scale'?
What is STMs full form?
LITNING
scanning tunneling microscope
Sahil
how nano science is used for hydrophobicity
Santosh
Do u think that Graphene and Fullrene fiber can be used to make Air Plane body structure the lightest and strongest. Rafiq
Rafiq
what is differents between GO and RGO?
Mahi
what is simplest way to understand the applications of nano robots used to detect the cancer affected cell of human body.? How this robot is carried to required site of body cell.? what will be the carrier material and how can be detected that correct delivery of drug is done Rafiq
Rafiq
if virus is killing to make ARTIFICIAL DNA OF GRAPHENE FOR KILLED THE VIRUS .THIS IS OUR ASSUMPTION
Anam
analytical skills graphene is prepared to kill any type viruses .
Anam
Any one who tell me about Preparation and application of Nanomaterial for drug Delivery
Hafiz
what is Nano technology ?
write examples of Nano molecule?
Bob
The nanotechnology is as new science, to scale nanometric
brayan
nanotechnology is the study, desing, synthesis, manipulation and application of materials and functional systems through control of matter at nanoscale
Damian
Is there any normative that regulates the use of silver nanoparticles?
what king of growth are you checking .?
Renato
What fields keep nano created devices from performing or assimulating ? Magnetic fields ? Are do they assimilate ?
why we need to study biomolecules, molecular biology in nanotechnology?
?
Kyle
yes I'm doing my masters in nanotechnology, we are being studying all these domains as well..
why?
what school?
Kyle
biomolecules are e building blocks of every organics and inorganic materials.
Joe
anyone know any internet site where one can find nanotechnology papers?
research.net
kanaga
sciencedirect big data base
Ernesto
Introduction about quantum dots in nanotechnology
hi
Loga
Got questions? Join the online conversation and get instant answers! By Joli Julianna By Marion Cabalfin By OpenStax By Janet Forrester By Megan Earhart By Richley Crapo By Jonathan Long By Stephen Voron By Mistry Bhavesh By OpenStax