Find Jobs
Hire Freelancers

alogorithm

$250-750 USD

Mbyllur
Postuar over 4 years ago

$250-750 USD

Paguhet në dorëzim
Goal: Use the agent to explore the Android UI to reach as many new UI states as possible. By exploring the states, agent hopes to find possible combinations of events/inputs that lead to unintended behavior like app crashes. I have integration Droidbot ([login to view URL]) with two agents: Actor Critic and DQN. Since I made it a gym environment, you can use any type of algorithm from any RL package that works with gym. I modified Droidbot to work as a gym environment. This allows you to integrate Droidbot with any major Reinforcement Learning library that works with gym environments (which is all of the major ones). I then intergrated the Droidbot gym environment with the Stable Baselines Reinforcement Learning library. I trained multiple agents and provided a script for running the Actor-Critic agent in the code's README file. This will generate an agent that learns to explore the android app UI and the agent will train a policy for the interaction. I also included a Deep Q Network agent and instructions for how to run that agent. I added an option to add unexplored events to the action space in the env so the agent can prioritize them. Going forward here are the issues and improvements that can be done: Modify the agent to prioritize taking unexplored events. Those unexplored events would then be added to the DQN agent's replay buffer. Only when the agent is choosing between explored events does the agent's selection process kick in. Explore parellelization for greater speed. Android emulators run a bit slow. Droidbot can be parallelized and RL libraries usually can though it's unclear the best way to do so. Train agents with various hyperparameters to find the ideal agent parameter settings. Decide on a better observation/state space representation. I created an observation space for the past four frames using image data. The papers you sent me all have different and interesting ways of doing the observation space representation before inputting it into the model. These are all quite involved and many possible choices can be made. I like the way Humanoid describes it and some code may be available from the github repo to make the transition easier. Decide on a better action space. This env is complicated because the number of actions at each step is different. I made the env so that the number can be regenerated at each step or fixed at the beginning. I defaulted it to a fixed number since RL libraries typically prefer it this way. You can do a variable number of actions but that typically involves inputting a state representation and an action representation into the model for each action, scoring them, and then taking the best one. However since there is no action representation, I couldn't model it that way. Humanoid has a good option for modelling action representations in either a fixed action space or a variable action space and some of the code may be available from that github repo. The other research papers you had have some other alternatives.
ID e Projektit: 20407556

Rreth projektit

9 propozime
Projekt në distancë
Aktive 5 yrs ago

Po kërkoni të fitoni para?

Përfitimet e ofertës për Freelancer

Vendosni buxhetin dhe afatin tuaj
Paguhuni për punën tuaj
Përshkruani propozimin tuaj
Është falas të regjistrohesh dhe të bësh oferta për punë
9 freelancers are bidding on average $506 USD for this job
Avatari i Përdoruesit
Hello, I have gone throw details of your project , i am highly experience developer and working with a small team as i have designer and developer for android ,ios and backed... as i have understood you need android UI .i have Strong knowledge of Logo Design, Graphic Design, UI/UX design principles,Photoshop, patterns with best practices. I can design it for you perfectly with all Feature & functionalities as you want. we can give you delivery like same you want , cost effective and time effective delivery. you could give me one chance as reply me IN CHAT window waiting for your response... Thanks
$250 USD në 11 ditë
4,7 (11 përshtypje)
5,4
5,4
Avatari i Përdoruesit
First:- Chatbot --> This can be integrated by any Facebook page, Slack etc. Its main aim is to reduce the human effort. For example, if this Chatbot is integrated with company page so it can easily answer you some basic questions about the company. Second:- Word Predictor --> This will be integrated with my Chatbot and it's an algorithm is such that it will learn according to previous input given and then It will suggest the next question and next word accordingly. Third:- Comment Checker --> This has a huge set of words inbuilt with its degree and level and it will analyze each comment and according to that it can give the report or if any inappropriate comment is taken it can forward to the authority. Speech Recognisation Train the database using deep learning, doing language model and lexical model for Arabic , adding functions to increase different types of noise at different levels as the picture shows. Then we notice the results.
$500 USD në 7 ditë
4,2 (7 përshtypje)
4,8
4,8
Avatari i Përdoruesit
Dear Client. First of all, it's my pleasure to bid on your project. I am very interested in your proposal. Because I have rich experience in this field. If you choose me, you'll never be disappointed in me, and I'll do my best for your project. Hope I will receive a positive response from your side that helps me in further. Sincerely wish your health. Best Regards!
$500 USD në 7 ditë
4,9 (4 përshtypje)
2,8
2,8
Avatari i Përdoruesit
Hi, I AM THE BEST CHOICE HERE. I am writing my thesis for my phd which is about RL and IRL, and all about the algorithms related. I am using gym and creating gym environments as well. I am a MuJoCo expert as well. I am working on humanoids and real human data by using the tools you mentioned
$750 USD në 7 ditë
0,0 (0 përshtypje)
0,0
0,0

Rreth klientit

Flamuri i KENYA
Kenya
0,0
0
Anëtar që nga korr 6, 2019

Verifikimi i klientit

Punë të tjera nga ky klient

CSV Converter
$250-750 USD
Faleminderit! Ne ju kemi dërguar me email një lidhje për të kërkuar kredinë tuaj falas.
Ndodhi një gabim gjatë dërgimit të email-it tuaj. Ju lutemi provoni përsëri.
Përdorues të regjistruar Punë të postuara
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Po ngarkohet shikimi paraprak
Leja u dha për Geolocation.
Seanca e hyrjes ka skaduar dhe ke dalë. Hyr sërish.