mathlab , Computer Engineering

Assignment Help:
Windy Grid World

This assignment is to use Reinforcement Learning to solve the following "Windy Grid World" problem illustrated in the above picture. Each cell in the image is a state. There are four actions: move up, down, left, and right. This is a deterministic domain -- each action deterministically moves the agent one cell in the direction indicated. If the agent is on the boundary of the world and executes an action that would move it "off" of the world, it remains on the grid in the same cell from which it executed the action.
Notice that there are arrows drawn in some states in the diagram. These are the "windy" states. In these states, the agent experiences an extra "push" upward. For example, if the agent is in a windy state and executes an action to the left or right, the result of the action is to move left or right (respectively) but also to move one cell upward. As a result, the agent moves diagonally upward to the left or right.
This is an episodic task where each episode lasts no more than 30 time steps. At the beginning of each episode, the agent is placed in the "Start" state. Reward in this domain is zero everywhere except when the agent is in the goal state (labeled "goal" in the diagram). The agent receives a reward of positive ten when it executes any action {\it from} the goal state. The episode ends after 30 time steps or when the agent takes any action after having landed in the goal state.
You should solve the problem using Q-learning. Use e-greedy exploration with epsilon=0.1 (the agent takes a random action 10 percent of the time in order to explore.) Use a learning rate of 0.1 and a discount rate of 0.9.
The programming should be done in MATLAB. Students may get access to MATLAB here. Alternatively, students may code in Python (using Numpy). If the student would rather code in a different language, please see Dr Platt or the TA.
Students should submit their homework via email to the TA ([email protected]) in the form of a ZIP file that includes the following:
1. A PDF of a plot of gridworld that illustrates the policy and a path found by Q-learning after it has approximately converged. The policy plot should identify the action taken by the policy in each state. The path should begin in the start state and follow the policy to the goal state.
2. A PDF of a plot of reward per episode. It should look like the diagram in Figure 6.13 in SB.
3. A text file showing output from a sample run of your code.
4. A directory containing all source code for your project.
5. A short readme file enumerating the important files in your submission.
Updates
You can initialize the Q function randomly or you can initialize it to a uniform value of 10. That is, you can initialize Q such that each value in the table is equal to 10.
There have been questions about how to know when the algorithm has converged. The algorithm has converged when the value function has stopped changing signficantly and the policy has stopped changing completely. Since we are using q-learning, the algorithm should converge to a single optimal policy.
Please also submit a short readme file with your homework that enumerates the important files in your submission.


Related Discussions:- mathlab

Give an example of first fit and best fit algorithms, Given memory partiti...

Given memory partitions of 100k, 500k, 200k, 300k, and 600k (in order), apply first fit and best fit algorithms to place processes with the space requirement of 212k, 417k, 112k an

Transaction, Explain Shadow Copy Scheme in detail.

Explain Shadow Copy Scheme in detail.

Explain passing parameters in general memory, Q. Explain Passing Parameters...

Q. Explain Passing Parameters in General Memory? The parameters can be passed in the memory too. In such a technique name of the memory location is used as a parameter. The res

What are stacks, What are stacks? A stack  is an abstract data type in...

What are stacks? A stack  is an abstract data type in which items are additional to and removed only from one end known as TOP. For example, consider the pile of papers on you

Name the numerous household devices, Name the Numerous household devices ...

Name the Numerous household devices Numerous household devices now use microprocessors to control their different functions. The following is just a sample of common devices (d

Explain difference between dynamic and static binding, Explain difference b...

Explain difference between Dynamic and static binding. Dynamic and static binding: Dynamic binding is a binding performed after the execution of a program has immediately beg

Determine the equivalent hexadecimal form of decimal number, Solve the equa...

Solve the equation 65.535 10 = X 16 Ans. In order to get X, convert the Decimal number 65.535 in its equal Hexadecimal form. So first taking 65 the integer part to convert in i

Define thread cancellation and target thread, Define thread cancellation & ...

Define thread cancellation & target thread.  The thread cancellation is the task of terminating a thread before it has done. A thread that is to be cancelled is often referred

Determine grade of service is given worse service or not, The larger the Gr...

The larger the Grade of Service, the worse is the service given, it is true or false. Ans: It is true that larger the Grade of Service, the worse service is provided.

What is a c++ class, Class is a user-defined data type in C++. It can be fo...

Class is a user-defined data type in C++. It can be formed to solve a particular kind of problem. After creation the user require not know the specifics of the working of a class.

Write Your Message!

Captcha
Free Assignment Quote

Assured A++ Grade

Get guaranteed satisfaction & time on delivery in every assignment order you paid with us! We ensure premium quality solution document along with free turntin report!

All rights reserved! Copyrights ©2019-2020 ExpertsMind IT Educational Pvt Ltd