Search Results

Search found 58 results on 3 pages for 'betamoo'.

Page 1/3 | 1 2 3  | Next Page >

  • Reinforcement learning in C#

    - by Betamoo
    I intend to use Reinforcement learning in my project but I do not know much how to implement it.. So I am looking for a library with different RL algorithms that I can use in my C# project.. Thanks Please Note: I found NeuronDotNet library for neural networks, I am now looking for RL library..

    Read the article

  • Reinforcement learning toy project

    - by Betamoo
    My toy project to learn & apply Reinforcement Learning is: - An agent tries to reach a goal state "safely" & "quickly".... - But there are projectiles and rockets that are launched upon the agent in the way. - The agent can determine rockets position -with some noise- only if they are "near" - The agent then must learn to avoid crashing into these rockets.. - The agent has -rechargable with time- fuel which is consumed in agent motion - Continuous Actions: Accelerating forward - Turning with angle I need some hints and names of RL algorithms that suit that case.. - I think it is POMDP , but can I model it as MDP and just ignore noise? - In case POMDP, What is the recommended way for evaluating probability? - Which is better to use in this case: Value functions or Policy Iterations? - Can I use NN to model environment dynamics instead of using explicit equations? - If yes, Is there a specific type/model of NN to be recommended? - I think Actions must be discretized, right? I know it will take time and effort to learn such a topic, but I am eager to.. You may answer some of the questions if you can not answer all... Thanks

    Read the article

  • Linux Shared Memory

    - by Betamoo
    The function which creates shared memory in *inux programming takes a key as one of its parameters.. What is the meaning of this key? And How can I use it? Edit: Not shared memory id

    Read the article

  • UDP Socket Client in .NET

    - by Betamoo
    I use UDP Sokckts in my client application. Here are some code snippets: SendIP = new IPEndPoint(IPAddress.Parse(IP), port); ReceiveIP = (EndPoint)(new IPEndPoint(IPAddress.Any, 0)); socket = new Socket( AddressFamily.InterNetwork, SocketType.Dgram, ProtocolType.Udp); socket.Bind(ReceiveIP); And to Receive (while(true)): byte[] data = new byte[BUFFERSIZE]; int receivedDataLength = socket.ReceiveFrom(data, ref ReceiveIP); string s= Encoding.ASCII.GetString(data, 0, receivedDataLength); I am doing an infinite while on the receive, there are other things to be done in the while, even if nothing is received.. I want to check if there are actually available data then receive else do not wait.. (Note the current receive method waits until the server sends a message)

    Read the article

  • Reinforcement learning with neural networks

    - by Betamoo
    I am working on a project with RL & NN I need to determine the action vector structure which will be fed to a neural network.. I have 3 different actions (A & B & Nothing) each with different powers (e.g A100 A50 B100 B50) I wonder what is the best way to feed these actions to a NN in order to yield best results? 1- feed A/B to input 1, while action power 100/50/Nothing to input 2 2- feed A100/A50/Nothing to input 1, while B100/B50/Nothing to input 2 3- feed A100/A50 to input 1, while B100/B50 to input 2, while Nothing flag to input 3 4- Also to feed 100 & 50 or normalize them to 2 & 1 ? I need reasons why to choose one method Any suggestions are recommended Thanks

    Read the article

  • Neural Network problems

    - by Betamoo
    I am using an external library for Artificial Neural Networks in my project.. While testing the ANN, It gave me output of all NaN (not a number in C#) The ANN has 8 input , 5 hidden , 5 hidden , 2 output, and all activation layers are of Linear type , and it uses back-propagation, with learning rate 0.65 I used one testcase for training { -2.2, 1.3, 0.4, 0.5, 0.1, 5, 3, -5 } ,{ -0.3, 0.2 } for 1000 epoch And I tested it on { 0.2, -0.2, 5.3, 0.4, 0.5, 0, 35, 0.0 } which gave { NaN , NaN} Note: this is one example of many that produces same case... I am trying to discover whether it is a bug in the library, or an illogical configuration.. The reasons I could think of for illogical configuration: All layers should not be linear Can not have descending size layers, i.e 8-5-5-2 is bad.. Only one testcase ? Values must be in range [0,1] or [-1,1] Is any of the above reasons could be the cause of error, or there are some constraints/rules that I do not know in ANN designing..? Note: I am newbie in ANN

    Read the article

  • C# Sorting Question

    - by betamoo
    I wonder what is the best C# data structure I should use to sort efficiently? Is it List or Array or what? And why the standard array [] does not implement sort method in it? Thanks

    Read the article

  • Writing an OS kernel in assembly with NASM

    - by Betamoo
    I want to know what is the standard way for writing a -simple- kernel to be compiled on NASM? To get it clearer: I was able to define the code block with all the following ways: [segment code] [segment .code] segment code segment .code [section code] [section .code] section code section .code I need to know what is the standard way to do that, And what is the difference between them... Thanks

    Read the article

  • Exceptions & Interrupts

    - by Betamoo
    When I was searching for a distinction between Exceptions and Interrupts, I found this question Interrupts and exceptions on SO... Some answers there were not suitable (at least for assembly level): "Exception are software-version of an interrupt" But there exist software interrupts!! "Interrupts are asynchronous but exceptions are synchronous" Is that right? "Interrupts occur regularly" "Interrupts are hardware implemented trap, exceptions are software implemented" Same as above! I need to find if some of these answers were right , also I would be grateful if anyone could provide a better answer... Thanks!

    Read the article

  • Array of Arrays in C#

    - by Betamoo
    I need to know how to initialize array of arrays in C#.. I know that there exist multidimensional array, but I think I do not need that in my case! I tried this code.. but could not know how to initialize with initializer list.. double[][] a=new double[2][];// ={{1,2},{3,4}}; Thank you PS: If you wonder why I use it: I need data structure that when I call obj[0] it returns an array.. I know it is strange.. Thanks

    Read the article

  • Reinforcement learning And POMDP

    - by Betamoo
    I am trying to use Multi-Layer NN to implement probability function in Partially Observable Markov Process.. I thought inputs to the NN would be: current state, selected action, result state; The output is a probability in [0,1] (prob. that performing selected action on current state will lead to result state) In training, I fed the inputs stated before, into the NN, and I taught it the output=1.0 for each case that already occurred. The problem : For nearly all test case the output probability is near 0.95.. no output was under 0.9 ! Even for nearly impossible results, it gave that high prob. PS:I think this is because I taught it happened cases only, but not un-happened ones.. But I can not at each step in the episode teach it the output=0.0 for every un-happened action! Any suggestions how to over come this problem? Or may be another way to use NN or to implement prob function? Thanks

    Read the article

  • Compiling linux sources in Windows enviroment

    - by Betamoo
    I got a source for console program written in c++ for linux I have got no experience with linux, and have no intend to install it. Is there a (automated) way to compile this source to run in windows? and what about linux functions and libraries called in this file? Thanks

    Read the article

  • C# Custom data type!

    - by Betamoo
    After I decided at last to implement my Int128 in C#, I thought it would be nice to make it look like other dotNet data types.. But I could not implement the following feature: suffix initialization: such as 13L and 0.2D Can I make my own suffix in C#? And if I can not.. how can I initialize it? i.e Int128 a= ??

    Read the article

  • C# Threads.Abort()

    - by Betamoo
    If a thread is running a function func1 that calls another function func2 inside it... Then I called thread.Abort() Will this stop func1 only OR func1 and func2 and all the functions func1 has called?? Thanks Edit: Here are more detail: func1 is called in a new thread, it continuously calls func2 on regular basis... func2 begin doing some work only if some array is not null.. it finishes it and return When supervisor wants to save data, it aborts Thread of func1- and then makes array null, saves data, then fill in the array with new one.. and starts Thread with func1 again.. Sometimes exception is raised because array is null in func2.. so func1 abort did not affect func2

    Read the article

  • Update Rule in Temporal difference

    - by Betamoo
    The update rule TD(0) Q-Learning: Q(t-1) = (1-alpha) * Q(t-1) + (alpha) * (Reward(t-1) + gamma* Max( Q(t) ) ) Then take either the current best action (to optimize) or a random action (to explorer) Where MaxNextQ is the maximum Q that can be got in the next state... But in TD(1) I think update rule will be: Q(t-2) = (1-alpha) * Q(t-2) + (alpha) * (Reward(t-2) + gamma * Reward(t-1) + gamma * gamma * Max( Q(t) ) ) My question: The term gamma * Reward(t-1) means that I will always take my best action at t-1 .. which I think will prevent exploring.. Can someone give me a hint? Thanks

    Read the article

  • math library in gcc

    - by Betamoo
    I am writing a program on linux gcc... When I tried to include <math.h> I found that I need to link math library by using command gcc -lm But I am searching for another way to link the math library 'in code', that does not require the user to compile using any options.. Can gcc -lm be done in c code using #pragma or something? EDIT: I have changed -ml to -lm

    Read the article

  • Communication protocols in UDP

    - by Betamoo
    After many hours, I have discovered that the given udp server needs the following steps for a successful communication: 1- Send "Start Message" on a given port 2- Wait to receive from server on any port 3- Then the port dedicated to you to send further data to the server equals the port you have received on it + 1 So I am asking if this kind is a known protocol/handshaking, or it is only special to this server?? PS: All above communication were in udp sockets in C# PS: Related to a previous question: http://stackoverflow.com/questions/2757868/about-c-udp-sockets Thanks

    Read the article

1 2 3  | Next Page >