COMP222程序辅导、写作Python程序语言

” COMP222程序辅导、写作Python程序语言COMP222 – 2018 – Second CA AssignmentIndividual courseworkTrain Deep Learning AgentsAssessment InformationAssignment Number 2 (of 2)Weighting 10%Assignment Circulated 16 November 2018Deadline Friday December 28, 15:00Submission Mode ElectronicLearning outcome Assessed 3. Ability to explain how deep neural networks are constructedand trained, and apply deep neural networksto work with large scale datasets4. Understand reinforcement learning, and is able todevelop deep reinforcement learning algorithms for suitableapplicationsPurpose of assessment To design and implement deep learning agents for eitherimage classification task or reinforcement learning task.Marking criteria The marking scheme can be found in Section 3.2Submission necessary in order Noto satisfy Module requirements?Late Submission Penalty Standard UoL Policy.11 ObjectiveThis assignment requires you to implement one of the following tasks:two image classifiers with convolutional neural networks,a deep reinforcement learning model for a video game from OpenAI Universe.Considering their di?erent dicultiesand the fact that the second needs at least an implementationof the first, we enable the possibility of getting 140% marks for the completion ofthe second.In the following, the Requirement and Description and the Marking Criteria for the twotasks are explained separately.2 CNN-based Image Classification2.1 Requirement And DescriptionLanguage and Platform Python (version 3.5 or above) and Tensorflow (newest version).You may use any libraries available on Python platform, such as numpy, scikit-learn, panda,etc.Dataset You can use any dataset which is convenient for you. Unless exceptional circumstance,it is recommended that the dataset is not too small (e.g., no less than 10,000items) and not too big (e.g., no more than 100,000 items). The images in the dataset arenot too large, as that will cost you too much time on training a good model. There are afew suggested datasets:MNIST handwritten dataset;CIFAR10 small image dataset;but you are encouraged to use your preferred dataset.Learning Task You need to train two classifiers on the chosen dataset.DNN Architecture There are a few existing DNN architectures for such small scale imagedataset, includingLeNet, see tutorial e.g., goo.gl/S6RQiSAlexNet, see tutorial e.g., goo.gl/UkjY6uBut you can design you own architecture.2Assignment Tasks The implementation task (as suggested in the Objective) is to learntwo models (of di?erent architecture) from the dataset you select. You need to write aproper document explaining the architectures, your training parameters, and the results(e.g., accuracy).Submission files You submission needs to contain the following two files:a package containing Your source codes (with the instruction on how to run them) anda document explaining your architectures, your training parameters, and the results.Detailed requirements on the document are given below.2.2 Marking CriteriaThe assignment is split in a number of steps. Every step gives you some marks. At thebeginning of the submitted document, please include a check list indicating whether thebelow marking points have been implemented successfully. Unless exceptional cases, thelength of the submitted document needs to be within 4 pages (A4 paper, 11pt or 12pt fontsize).Step 1: Loading Data 10%Successfully load the dataset and use python commands to display the dataset information,e.g., the number of data entries, the number of classes, number of data entries for eachclasses, etc.Step 2: Write two CNN models 20%Write your CNN models with tensorflow. To get the marks, you need to explain in thedocument what the inputs and outputs are and what the hidden layers are.Step 3: Train your CNN models 30%To get the marks, you need to explain in the document the training parameters, e.g., learningrate, loss function, etc, and the accuracy of your resulting models over testing dataset.Step 4: Predict with Trained Model, 20%You need to be able to predict the class label by giving an image. For example, predict thelabel for the 100th image in the MNIST test dataset. To get the marks, you need to clearlyidentify in the document which part of the code is for this purpose.32.3 Extra 20%You can see that marks for the steps described add up to 80%. In order to get 20% extrayou have to be creative. For Example (you are encouraged to not follow this example), youmay adjust your models by adding or removing some layers and compare the performanceof the resulting models. You are expecected to have a clear explanation on what you havedone and what you have observed.3 Deep Reinforcement Learning3.1 Requirement and DescriptionLanguage and Platform Python (version 3.5 or above) and Tensorflow (newest version).You may use any libraries available on Python platform, such as numpy, scikit-learn,panda, etc. You may also need to install OpenAI universe ( httpss://github.com/openai/universe) if you choose the second challenge.Dataset You can use any game in OpenAI universe or OpenAI gym.Learning Task You need to train a deep reinforcement learning model to play the gameyou selected.DNN Architecture There are a few existing deep reinforcement models, includingDeep Q-NetworkDouble Q-LearningActor-Critic algorithmYou are able to find various tutorials and implemenations from Github, for example goo.gl/1q6L31.Assignment Tasks The implementation task (as suggested in the Objective) is to traina deep reinforcement agent for a simple video game. Here, the main task is not to design anew algorithm, but to get yourself familiar with the concept of reinforcement learning andunderstand how the existing methods work.Submission files You submission needs to contain the following two files:a package containing your source codes (with the instruction on how to run them) anda document Explaining your Connection to openAI universe/gym, your network architectures,your training parameters, and the results. Detailed requirements on thedocument are given below.43.2 Marking CriteriaThe assignment is split in a number of steps. Every step gives you some marks.Step 1: Import an OpenAI universe/gym game 20%As the starting point, you need to import a game.Step 2: Creating a network 20%You need to use a deep neural network.Step 3: Connection of the game to the network 10%You will need to explicitly Associate the observations, actions, and rewards of the game tothe networks input and output. Clearly identify this part of the code in your document.Step 4: Deep reinforcement learning model 30%This part is for dierent Deep reinforcement learning models. You need to clearly state whichmodel you are using, the parameters of the model, and how do you train/update the model.Step 5: Experimental results 20%You may record a video demo to exhibit what your agent can do. Alternatively, you candescribe in details with texts.4 Deadlines and How to SubmitDeadline for submitting the Second assignment is Friday, 28 December 2018 at 3pm.Submission is via the departmental submission system accessible (from within the department)from请加QQ：99515681 或邮箱：99515681@qq.com WX：codehelp

“