Reinforcement learning with neural networks

  • 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


-------------Problems Reply------------

What do you want to learn? What should be the output? Is the input just the used action? If you are learning a model of the environment, it is expressed by a probability distribution:

P(next_state|state, action)

It is common to use a separate model for each action. That makes the mapping between input and output simpler. The input is a vector of state features. The output is a vector of the features of the next state. The used action is implied by the model.

The state features could be encoded as bits. An active bit would indicate the presence of a feature.

This would learn a deterministic model. I don't know what is a good way to learn a stochastic model of the next states. One possibility may be to use stochastic neurons.

Category:machine learning Views:1 Time:2010-05-01

Related post

  • How to make virtual organisms learn using neural networks? 2012-01-25

    I'm making a simple learning simulation, where there are multiple organisms on screen. They're supposed to learn how to eat, using their simple neural networks. They have 4 neurons, and each neuron activates movement in one direction (it's a 2D plane

  • Competitive Learning in Neural Networks 2009-11-16

    I am playing with some neural network simulations. I'd like to get two neural networks sharing the input and output nodes (with other nodes being distinct and part of two different routes) to compete. Are there any examples/standard algorithms I shou

  • Neural Network Not Learning, Converging on one output 2014-05-07

    I am trying to program a neural network and I am now testing it. I have simplified it down to 2 training examples with 2 inputs and 1 input. Input : Output 1,0 : 1 1,1 : 0 I cycle through forward and back-propogation 1,000 times and the network outpu

  • Prototyping neural networks 2009-12-04

    from your experience, which is the most effective approach to implement artificial neural networks prototypes? It is a lot of hype about R (free, but I didn't work with it) or Matlab (not free), another possible choice is to use a language like C++/J

  • Prerequisites Needed to Read Books on Neural Networks (and understand them) 2008-12-03

    I've been trying to learn about Neural Networks for a while now, and I can understand some basic tutorials online, and I've been able to get through portions of Neural Computing - An Introduction but even there, I'm glazing over a lot of the math, an

  • Looking for a Good Reference on Neural Networks 2009-03-02

    Duplicate I'm looking for a good (beginner level) reference book (or website) on different types of Neural Nets/their applications/examples. I d

  • Where to start Handwritten Recognition using Neural Network? 2009-12-28

    I've been trying to learn about Neural Networks for a while now, and I can understand some basic tutorials online. Now i want to develop online handwritten recognition using Neural Network. So i haven't any idea where to start? And i need a very good

  • Why do we use neural networks in computers? 2010-07-01

    Why do we use neural networks? It's biologic. Aren't there any more solutions that're more "suitable" for computers? In other words: Why do we use the human brain as a model for inspiration for artifical intelligence? --------------Solutions---------

  • Neural network weighting 2010-11-15

    Recently I've studied the backpropagation network and have done some manual exercise. After that, I came up with a question( maybe doesn't make sense): is there any thing important in following two different replacement methods: 1. Incremental Traini

  • All information about Neural Network 2011-01-02

    I heard about Neural Network but there are so many resources and i want to know concrete use of it and if possible some small code source with comment. ^^ --------------Solutions------------- you might find the following questions to be of use: What

  • Neural Network, Genetic algorithm as an Intrusion detection system 2011-05-30

    Hi I need some help on getting started with creating my first algorithm; I want to create a NN/Genetic Algorithm for use as an Intrusion detection system. But I’m struggling with some points (never written an algorithm before.) I want to develop in C

  • XOR Hebbian test/example neural network 2011-09-04

    I just finished writing some code that runs a hebbian learning feedforward neural network. I've done a back propagation neural network before and the first thing i did to make sure it worked was too try the XOR problem. What should i do to test my he

  • When referring to Neural Networks, what is a "control task" or "controller design"? 2011-12-26

    It seems that there are certain machine learning algorithms out there that are most suitable for "control tasks" and "controller designs". I know that there's a lot of different ways for the word "control" to be defined/interpreted, so I was wonderin

  • training feedforward neural network for OCR 2012-03-13

    currently im learning about neural networks and im trying to create an application that can be trained to recognize handwritten characters. for this problem i use a feedforward neural network and it seems to work when i train it to recognize 1, 2 or

  • What are the uses of recurrent neural networks when using them with Reinforcement Learning? 2009-11-23

    I do know that feedforward multi-layer neural networks with backprop are used with Reinforcement Learning as to help it generalize the actions our agent does. This is, if we have a big state space, we can do some actions, and they will help generaliz

  • Support Vector Machines - Better than Artificial Neural Networks in which learning situations? 2011-07-14

    I know SVMs are supposedly 'ANN killers' in that they automatically select representation complexity and find a global optimum (see here for some SVM praising quotes). But here is where I'm unclear -- do all of these claims of superiority hold for ju

  • Neural networks - why so many learning rules? 2010-01-23

    I'm starting neural networks, currently following mostly D. Kriesel's tutorial. Right off the beginning it introduces at least three (different?) learning rules (Hebbian, delta rule, backpropagation) concerning supervised learning. I might be missing

  • Learning AI by practice ( Perceptrons, Neural networks and Bayesian AI) 2010-08-23

    I'm about to take a course in AI and I want to practice before. I'm using a book to learn the theory, but resources and concrete examples in any language to help with the practice would be amazing. Can anyone recommend me good sites or books with ple

  • How do I decide which Neural Network and learning method to use in a particular case? 2010-09-29

    I am new in neural networks and I need to determine the pattern among a given set of inputs and outputs. So how do I decide which neural network to use for training or even which learning method to use? I have little idea about the pattern or relatio

Copyright (C), All Rights Reserved.

processed in 0.168 (s). 11 q(s)