Search Results

Search found 1366 results on 55 pages for 'artificial intelligence'.

Page 14/55 | < Previous Page | 10 11 12 13 14 15 16 17 18 19 20 21  | Next Page >

• method for specialized pathfinding?

  - by rlbond

  I am working on a roguelike in my (very little) free time. Each level will basically be a few rectangular rooms connected together by paths. I want the paths between rooms to be natural-looking and windy, however. For example, I would not consider the following natural-looking: B X X X XX XX XX AXX I really want something more like this: B X XXXX X X X X AXXXXXXXX These paths must satisfy a few properties: I must be able to specify an area inside which they are bounded, I must be able to parameterize how windy and lengthy they are, The lines should not look like they started at one path and ended at the other. For example, the first example above looks as if it started at A and ended at B, because it basically changed directions repeatedly until it lined up with B and then just went straight there. I was hoping to use A*, but honestly I have no idea what my heuristic would be. I have also considered using a genetic algorithm, but I don't know how practical that method might end up. My question is, what is a good way to get the results I want? Please do not just specify a method like "A*" or "Dijkstra's algorithm," because I also need help with a good heuristic.

  Read the article

• Finding minimum cut-sets between bounded subgraphs

  - by Tore

  If a game map is partitioned into subgraphs, how to minimize edges between subgraphs? I have a problem, Im trying to make A* searches through a grid based game like pacman or sokoban, but i need to find "enclosures". What do i mean by enclosures? subgraphs with as few cut edges as possible given a maximum size and minimum size for number of vertices for each subgraph that act as a soft constraints. Alternatively you could say i am looking to find bridges between subgraphs, but its generally the same problem. Given a game that looks like this, what i want to do is find enclosures so that i can properly find entrances to them and thus get a good heuristic for reaching vertices inside these enclosures. So what i want is to find these colored regions on any given map. My Motivation The reason for me bothering to do this and not just staying content with the performance of a simple manhattan distance heuristic is that an enclosure heuristic can give more optimal results and i would not have to actually do the A* to get some proper distance calculations and also for later adding competitive blocking of opponents within these enclosures when playing sokoban type games. Also the enclosure heuristic can be used for a minimax approach to finding goal vertices more properly. A possible solution to the problem is the Kernighan-Lin algorithm: function Kernighan-Lin(G(V,E)): determine a balanced initial partition of the nodes into sets A and B do A1 := A; B1 := B compute D values for all a in A1 and b in B1 for (i := 1 to |V|/2) find a[i] from A1 and b[i] from B1, such that g[i] = D[a[i]] + D[b[i]] - 2*c[a][b] is maximal move a[i] to B1 and b[i] to A1 remove a[i] and b[i] from further consideration in this pass update D values for the elements of A1 = A1 / a[i] and B1 = B1 / b[i] end for find k which maximizes g_max, the sum of g[1],...,g[k] if (g_max > 0) then Exchange a[1],a[2],...,a[k] with b[1],b[2],...,b[k] until (g_max <= 0) return G(V,E) My problem with this algorithm is its runtime at O(n^2 * lg(n)), i am thinking of limiting the nodes in A1 and B1 to the border of each subgraph to reduce the amount of work done. I also dont understand the c[a][b] cost in the algorithm, if a and b do not have an edge between them is the cost assumed to be 0 or infinity, or should i create an edge based on some heuristic. Do you know what c[a][b] is supposed to be when there is no edge between a and b? Do you think my problem is suitable to use a multi level problem? Why or why not? Do you have a good idea for how to reduce the work done with the kernighan-lin algorithm for my problem?

  Read the article

• Any good card game AI strategies?

  - by Mark

  What would be strategies for writing a good computer opponent for a card game? Most card games are games of incomplete information, so simply mapping out and traversing the game tree as one could do with a board game does not seem too promising. Maybe one could track what open cards are in the game (as soon as they are revealed) and assign probabilities to certain events (e.g. opponent still has 2 cards of clubs). Does anyone have experience with this? Links and directions greatly appreciated. Thanks! -Mark

  Read the article

• Calculating Nearest Match to Mean/Stddev Pair With LibSVM

  - by Chris S

  I'm new to SVMs, and I'm trying to use the Python interface to libsvm to classify a sample containing a mean and stddev. However, I'm getting nonsensical results. Is this task inappropriate for SVMs or is there an error in my use of libsvm? Below is the simple Python script I'm using to test: #!/usr/bin/env python # Simple classifier test. # Adapted from the svm_test.py file included in the standard libsvm distribution. from collections import defaultdict from svm import * # Define our sparse data formatted training and testing sets. labels = [1,2,3,4] train = [ # key: 0=mean, 1=stddev {0:2.5,1:3.5}, {0:5,1:1.2}, {0:7,1:3.3}, {0:10.3,1:0.3}, ] problem = svm_problem(labels, train) test = [ ({0:3, 1:3.11},1), ({0:7.3,1:3.1},3), ({0:7,1:3.3},3), ({0:9.8,1:0.5},4), ] # Test classifiers. kernels = [LINEAR, POLY, RBF] kname = ['linear','polynomial','rbf'] correct = defaultdict(int) for kn,kt in zip(kname,kernels): print kt param = svm_parameter(kernel_type = kt, C=10, probability = 1) model = svm_model(problem, param) for test_sample,correct_label in test: pred_label, pred_probability = model.predict_probability(test_sample) correct[kn] += pred_label == correct_label # Show results. print '-'*80 print 'Accuracy:' for kn,correct_count in correct.iteritems(): print '\t',kn, '%.6f (%i of %i)' % (correct_count/float(len(test)), correct_count, len(test)) The domain seems fairly simple. I'd expect that if it's trained to know a mean of 2.5 means label 1, then when it sees a mean of 2.4, it should return label 1 as the most likely classification. However, each kernel has an accuracy of 0%. Why is this? On a side note, is there a way to hide all the verbose training output dumped by libsvm in the terminal? I've searched libsvm's docs and code, but I can't find any way to turn this off.

  Read the article

• What problems have you solved using genetic algorithms/genetic programming?

  - by knorv

  Genetic algorithms (GA) and genetic programming (GP) are interesting areas of research. I'd like to know about specific problems you - the SO reader - have solved using GA/GP and what libraries/frameworks you used if you didn't roll your own. Questions: What problems have you used GA/GP to solve? What libraries/frameworks did you use? I'm looking for first-hand experiences, so please do not answer unless you have that.

  Read the article

• Extracting pure content / text from HTML Pages by excluding navigation and chrome content

  - by Ankur Gupta

  Hi, I am crawling news websites and want to extract News Title, News Abstract (First Paragraph), etc I plugged into the webkit parser code to easily navigate webpage as a tree. To eliminate navigation and other non news content I take the text version of the article (minus the html tags, webkit provides api for the same). Then I run the diff algorithm comparing various article's text from same website this results in similar text being eliminated. This gives me content minus the common navigation content etc. Despite the above approach I am still getting quite some junk in my final text. This results in incorrect News Abstract being extracted. The error rate is 5 in 10 article i.e. 50%. Error as in Can you Suggest an alternative strategy for extraction of pure content, Would/Can learning Natural Language rocessing help in extracting correct abstract from these articles ? How would you approach the above problem ?. Are these any research papers on the same ?. Regards Ankur Gupta

  Read the article

• Strategy and AI for the game 'Proximity'

  - by smci

  'Proximity' is a strategy game of territorial domination similar to Othello, Go and Risk. Two players, uses a 10x12 hex grid. Game invented by Brian Cable in 2007. Seems to be a worthy game for discussing a) optimal strategy then b) how to build an AI Strategies are going to be probabilistic or heuristic-based, due to the randomness factor, and the high branching factor (starts out at 120). So it will be kind of hard to compare objectively. A compute time limit of 5s per turn seems reasonable. Game: Flash version here and many copies elsewhere on the web Rules: here Object: to have control of the most armies after all tiles have been placed. Each turn you received a randomly numbered tile (value between 1 and 20 armies) to place on any vacant board space. If this tile is adjacent to any ally tiles, it will strengthen each tile's defenses +1 (up to a max value of 20). If it is adjacent to any enemy tiles, it will take control over them if its number is higher than the number on the enemy tile. Thoughts on strategy: Here are some initial thoughts; setting the computer AI to Expert will probably teach a lot: minimizing your perimeter seems to be a good strategy, to prevent flips and minimize worst-case damage like in Go, leaving holes inside your formation is lethal, only more so with the hex grid because you can lose armies on up to 6 squares in one move low-numbered tiles are a liability, so place them away from your main territory, near the board edges and scattered. You can also use low-numbered tiles to plug holes in your formation, or make small gains along the perimeter which the opponent will not tend to bother attacking. a triangle formation of three pieces is strong since they mutually reinforce, and also reduce the perimeter Each tile can be flipped at most 6 times, i.e. when its neighbor tiles are occupied. Control of a formation can flow back and forth. Sometimes you lose part of a formation and plug any holes to render that part of the board 'dead' and lock in your territory/ prevent further losses. Low-numbered tiles are obvious-but-low-valued liabilities, but high-numbered tiles can be bigger liabilities if they get flipped (which is harder). One lucky play with a 20-army tile can cause a swing of 200 (from +100 to -100 armies). So tile placement will have both offensive and defensive considerations. Comment 1,2,4 seem to resemble a minimax strategy where we minimize the maximum expected possible loss (modified by some probabilistic consideration of the value ß the opponent can get from 1..20 i.e. a structure which can only be flipped by a ß=20 tile is 'nearly impregnable'.) I'm not clear what the implications of comments 3,5,6 are for optimal strategy. Interested in comments from Go, Chess or Othello players. (The sequel ProximityHD for XBox Live, allows 4-player -cooperative or -competitive local multiplayer increases the branching factor since you now have 5 tiles in your hand at any given time, of which you can only play one. Reinforcement of ally tiles is increased to +2 per ally.)

  Read the article

• Resilient backpropagation neural network - question about gradient

  - by Raf

  Hello Guys, First I want to say that I'm really new to neural networks and I don't understand it very good ;) I've made my first C# implementation of the backpropagation neural network. I've tested it using XOR and it looks it work. Now I would like change my implementation to use resilient backpropagation (Rprop - http://en.wikipedia.org/wiki/Rprop). The definition says: "Rprop takes into account only the sign of the partial derivative over all patterns (not the magnitude), and acts independently on each "weight". Could somebody tell me what partial derivative over all patterns is? And how should I compute this partial derivative for a neuron in hidden layer. Thanks a lot UPDATE: My implementation base on this Java code: www_.dia.fi.upm.es/~jamartin/downloads/bpnn.java My backPropagate method looks like this: public double backPropagate(double[] targets) { double error, change; // calculate error terms for output double[] output_deltas = new double[outputsNumber]; for (int k = 0; k < outputsNumber; k++) { error = targets[k] - activationsOutputs[k]; output_deltas[k] = Dsigmoid(activationsOutputs[k]) * error; } // calculate error terms for hidden double[] hidden_deltas = new double[hiddenNumber]; for (int j = 0; j < hiddenNumber; j++) { error = 0.0; for (int k = 0; k < outputsNumber; k++) { error = error + output_deltas[k] * weightsOutputs[j, k]; } hidden_deltas[j] = Dsigmoid(activationsHidden[j]) * error; } //update output weights for (int j = 0; j < hiddenNumber; j++) { for (int k = 0; k < outputsNumber; k++) { change = output_deltas[k] * activationsHidden[j]; weightsOutputs[j, k] = weightsOutputs[j, k] + learningRate * change + momentumFactor * lastChangeWeightsForMomentumOutpus[j, k]; lastChangeWeightsForMomentumOutpus[j, k] = change; } } // update input weights for (int i = 0; i < inputsNumber; i++) { for (int j = 0; j < hiddenNumber; j++) { change = hidden_deltas[j] * activationsInputs[i]; weightsInputs[i, j] = weightsInputs[i, j] + learningRate * change + momentumFactor * lastChangeWeightsForMomentumInputs[i, j]; lastChangeWeightsForMomentumInputs[i, j] = change; } } // calculate error error = 0.0; for (int k = 0; k < outputsNumber; k++) { error = error + 0.5 * (targets[k] - activationsOutputs[k]) * (targets[k] - activationsOutputs[k]); } return error; } So can I use change = hidden_deltas[j] * activationsInputs[i] variable as a gradient (partial derivative) for checking the sing?

  Read the article

• How does Dijkstra's Algorithm and A-Star compare?

  - by KingNestor

  I was looking at what the guys in the Mario AI Competition have been doing and some of them have built some pretty neat Mario bots utilizing the A* (A-Star) Pathing Algorithm. (Video of Mario A* Bot In Action) My question is, how does A-Star compare with Dijkstra? Looking over them, they seem similar. Why would someone use one over the other? Especially in the context of pathing in games?

  Read the article

• How do you solve the 15-puzzle with A-Star or Dijkstra's Algorithm?

  - by Sean

  I've read in one of my AI books that popular algorithms (A-Star, Dijkstra) for path-finding in simulation or games is also used to solve the well-known "15-puzzle". Can anyone give me some pointers on how I would reduce the 15-puzzle to a graph of nodes and edges so that I could apply one of these algorithms? If I were to treat each node in the graph as a game state then wouldn't that tree become quite large? Or is that just the way to do it?

  Read the article

• Heuristic to identify if a series of 4 bytes chunks of data are integers or floats

  - by flint

  What's the best heuristic I can use to identify whether a chunk of X 4-bytes are integers or floats? A human can do this easily, but I wanted to do it programmatically. I realize that since every combination of bits will result in a valid integer and (almost?) all of them will also result in a valid float, there is no way to know for sure. But I still would like to identify the most likely candidate (which will virtually always be correct; or at least, a human can do it). For example, let's take a series of 4-bytes raw data and print them as integers first and then as floats: 1 1.4013e-45 10 1.4013e-44 44 6.16571e-44 5000 7.00649e-42 1024 1.43493e-42 0 0 0 0 -5 -nan 11 1.54143e-44 Obviously they will be integers. Now, another example: 1065353216 1 1084227584 5 1085276160 5.5 1068149391 1.33333 1083179008 4.5 1120403456 100 0 0 -1110651699 -0.1 1195593728 50000 These will obviously be floats. PS: I'm using C++ but you can answer in any language, pseudo code or just in english.

  Read the article

• Machine Learning Algorithm for Predicting Order of Events?

  - by user213060

  Simple machine learning question. Probably numerous ways to solve this: There is an infinite stream of 4 possible events: 'event_1', 'event_2', 'event_4', 'event_4' The events do not come in in completely random order. We will assume that there are some complex patterns to the order that most events come in, and the rest of the events are just random. We do not know the patterns ahead of time though. After each event is received, I want to predict what the next event will be based on the order that events have come in in the past. The predictor will then be told what the next event actually was: Predictor=new_predictor() prev_event=False while True: event=get_event() if prev_event is not False: Predictor.last_event_was(prev_event) predicted_event=Predictor.predict_next_event(event) The question arises of how long of a history that the predictor should maintain, since maintaining infinite history will not be possible. I'll leave this up to you to answer. The answer can't be infinte though for practicality. So I believe that the predictions will have to be done with some kind of rolling history. Adding a new event and expiring an old event should therefore be rather efficient, and not require rebuilding the entire predictor model, for example. Specific code, instead of research papers, would add for me immense value to your responses. Python or C libraries are nice, but anything will do. Thanks! Update: And what if more than one event can happen simultaneously on each round. Does that change the solution?

  Read the article

• RTS AI: where to start?

  - by awegawef

  I'd like to begin tinkering around with an RTS AI, but I'm having trouble finding a good environment to work with, ie a game that has been already created. I have looked at Spring RTS and Bos Wars, but they don't seem to be conducive to creating simple examples. I am not totally opposed to writing my own game environment, it would just take a long time. Does anyone have a suggestion as to how I can get my feet wet without programming my own game?

  Read the article

• ai: Determining what tests to run to get most useful data

  - by Sai Emrys

  This is for http://cssfingerprint.com I have a system (see about page on site for details) where: I need to output a ranked list, with confidences, of categories that match a particular feature vector the binary feature vectors are a list of site IDs & whether this session detected a hit feature vectors are, for a given categorization, somewhat noisy (sites will decay out of history, and people will visit sites they don't normally visit) categories are a large, non-closed set (user IDs) my total feature space is approximately 50 million items (URLs) for any given test, I can only query approx. 0.2% of that space I can only make the decision of what to query, based on results so far, ~10-30 times, and must do so in <~100ms (though I can take much longer to do post-processing, relevant aggregation, etc) getting the AI's probability ranking of categories based on results so far is mildly expensive; ideally the decision will depend mostly on a few cheap sql queries I have training data that can say authoritatively that any two feature vectors are the same category but not that they are different (people sometimes forget their codes and use new ones, thereby making a new user id) I need an algorithm to determine what features (sites) are most likely to have a high ROI to query (i.e. to better discriminate between plausible-so-far categories [users], and to increase certainty that it's any given one). This needs to take into balance exploitation (test based on prior test data) and exploration (test stuff that's not been tested enough to find out how it performs). There's another question that deals with a priori ranking; this one is specifically about a posteriori ranking based on results gathered so far. Right now, I have little enough data that I can just always test everything that anyone else has ever gotten a hit for, but eventually that won't be the case, at which point this problem will need to be solved. I imagine that this is a fairly standard problem in AI - having a cheap heuristic for what expensive queries to make - but it wasn't covered in my AI class, so I don't actually know whether there's a standard answer. So, relevant reading that's not too math-heavy would be helpful, as well as suggestions for particular algorithms. What's a good way to approach this problem?

  Read the article

• Evolutionary Algorithms: Optimal Repopulation Breakdowns

  - by Brian MacKay

  It's really all in the title, but here's a breakdown for anyone who is interested in Evolutionary Algorithms: In an EA, the basic premise is that you randomly generate a certain number of organisms (which are really just sets of parameters), run them against a problem, and then let the top performers survive. You then repopulate with a combination of crossbreeds of the survivors, mutations of the survivors, and also a certain number of new random organisms. Do that several thousand times, and efficient organisms arise. Some people also do things like introduce multiple "islands" of organisms, which are seperate populations that are allowed to crossbreed once in awhile. So, my question is: what are the optimal repopulation percentages? I have been keeping the top 10% performers, and repopulating with 30% crossbreeds and 30% mutations. The remaining 30% is for new organisms. I have also tried out the multiple island theory, and I'm interested in your results on that as well. It is not lost on me that this is exactly the type of problem an EA could solve. Are you aware of anyone trying that? Thanks in advance!

  Read the article

• Tic-Tac-Toe AI: How to Make the Tree?

  - by cam

  I'm having a huge block trying to understand "trees" while making a Tic-Tac-Toe bot. I understand the concept, but I can't figure out to implement them. Can someone show me an example of how a tree should be generated for such a case? Or a good tutorial on generating trees? I guess the hard part is generating partial trees. I know how to implement generating a whole tree, but not parts of it.

  Read the article

• Find optimal strategy and AI for the game 'Proximity'?

  - by smci

  'Proximity' is a strategy game of territorial domination similar to Othello, Go and Risk. Two players, uses a 10x12 hex grid. Game invented by Brian Cable in 2007. Seems to be a worthy game for discussing a) optimal algorithm then b) how to build an AI. Strategies are going to be probabilistic or heuristic-based, due to the randomness factor, and the insane branching factor (20^120). So it will be kind of hard to compare objectively. A compute time limit of 5s per turn seems reasonable. Game: Flash version here and many copies elsewhere on the web Rules: here Object: to have control of the most armies after all tiles have been placed. Each turn you received a randomly numbered tile (value between 1 and 20 armies) to place on any vacant board space. If this tile is adjacent to any ally tiles, it will strengthen each tile's defenses +1 (up to a max value of 20). If it is adjacent to any enemy tiles, it will take control over them if its number is higher than the number on the enemy tile. Thoughts on strategy: Here are some initial thoughts; setting the computer AI to Expert will probably teach a lot: minimizing your perimeter seems to be a good strategy, to prevent flips and minimize worst-case damage like in Go, leaving holes inside your formation is lethal, only more so with the hex grid because you can lose armies on up to 6 squares in one move low-numbered tiles are a liability, so place them away from your main territory, near the board edges and scattered. You can also use low-numbered tiles to plug holes in your formation, or make small gains along the perimeter which the opponent will not tend to bother attacking. a triangle formation of three pieces is strong since they mutually reinforce, and also reduce the perimeter Each tile can be flipped at most 6 times, i.e. when its neighbor tiles are occupied. Control of a formation can flow back and forth. Sometimes you lose part of a formation and plug any holes to render that part of the board 'dead' and lock in your territory/ prevent further losses. Low-numbered tiles are obvious-but-low-valued liabilities, but high-numbered tiles can be bigger liabilities if they get flipped (which is harder). One lucky play with a 20-army tile can cause a swing of 200 (from +100 to -100 armies). So tile placement will have both offensive and defensive considerations. Comment 1,2,4 seem to resemble a minimax strategy where we minimize the maximum expected possible loss (modified by some probabilistic consideration of the value ß the opponent can get from 1..20 i.e. a structure which can only be flipped by a ß=20 tile is 'nearly impregnable'.) I'm not clear what the implications of comments 3,5,6 are for optimal strategy. Interested in comments from Go, Chess or Othello players. (The sequel ProximityHD for XBox Live, allows 4-player -cooperative or -competitive local multiplayer increases the branching factor since you now have 5 tiles in your hand at any given time, of which you can only play one. Reinforcement of ally tiles is increased to +2 per ally.)

  Read the article

• Self organising Maps - Explanation required in layman terms

  - by karthi

  Hi, I need to develop a flash tutorial on Self organizing maps (in neural networks) to make people understand it easily. I need some good example so that even a beginner can understand it easily. Please help me with some examples, links with simple examples. Thanks in advance

  Read the article

• Applications for the Church Programming Language

  - by Chris S

  Has anyone worked with the programming language Church? Can anyone recommend practical applications? I just discovered it, and while it sounds like it addresses some long-standing problems in AI and machine-learning, I'm sceptical. I had never heard of it, and was surprised to find it's actually been around for a few years, having been announced in the paper Church: a language for generative models.

  Read the article

• Implementing crossover in genetic programming

  - by Name

  Hi, I'm writing a genetic programming (GP) system (in C but that's a minor detail). I've read a lot of the literature (Koza, Poli, Langdon, Banzhaf, Brameier, et al) but there are some implementation details I've never seen explained. For example: I'm using a steady state population rather than a generational approach, primarily to use all of the computer's memory rather than reserve half for the interim population. Q1. In GP, as opposed to GA, when you perform crossover you select two parents but do you create one child or two, or is that a free choice you have? Q2. In steady state GP, as opposed to a generational system, what members of the population do the children created by crossover replace? This is what I haven't seen discussed. Is it the two parents, or is it two other, randomly-selected members? I can understand if it's the latter, and that you might use negative tournament selection to choose members to replace, but would that not create premature convergence? (After a crossover event the population contains the two original parents plus two children of those parents, and two other random members get removed. Elitism is inherent.) Q3. Is there a Web forum or mailing list focused on GP? Oddly I haven't found one. Yahoo's GP group is used almost exclusively for announcements, the Poli/Langdon Field Guide forum is almost silent, and GP discussions on general/game programming sites like gamedev.net are very basic. Thanks for any help you can provide!

  Read the article

• Rush Hour - Solving the game

  - by Rubys

  Rush Hour if you're not familiar with it, the game consists of a collection of cars of varying sizes, set either horizontally or vertically, on a NxM grid that has a single exit. Each car can move forward/backward in the directions it's set in, as long as another car is not blocking it. You can never change the direction of a car. There is one special car, usually it's the red one. It's set in the same row that the exit is in, and the objective of the game is to find a series of moves (a move - moving a car N steps back or forward) that will allow the red car to drive out of the maze. I've been trying to think how to solve this problem computationally, and I can really not think of any good solution. I came up with a few: Backtracking. This is pretty simple - Recursion and some more recursion until you find the answer. However, each car can be moved a few different ways, and in each game state a few cars can be moved, and the resulting game tree will be HUGE. Some sort of constraint algorithm that will take into account what needs to be moved, and work recursively somehow. This is a very rough idea, but it is an idea. Graphs? Model the game states as a graph and apply some sort of variation on a coloring algorithm, to resolve dependencies? Again, this is a very rough idea. A friend suggested genetic algorithms. This is sort of possible but not easily. I can't think of a good way to make an evaluation function, and without that we've got nothing. So the question is - How to create a program that takes a grid and the vehicle layout, and outputs a series of steps needed to get the red car out? Sub-issues: Finding some solution. Finding an optimal solution (minimal number of moves) Evaluating how good a current state is Example: How can you move the cars in this setting, so that the red car can "exit" the maze through the exit on the right?

  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

• Good implementations of reinforced learning?

  - by Paperino

  For an ai-class project I need to implement a reinforcement learning algorithm which beats a simple game of tetris. The game is written in Java and we have the source code. I know the basics of reinforcement learning theory but was wondering if anyone in the SO community had hands on experience with this type of thing. What would your recommended readings be for an implementation of reinforced learning in a tetris game? Are there any good open source projects that accomplish similar things that would be worth checking out? Thanks in advanced Edit: The more specific the better, but general resources about the subject are welcomed. Follow up: Thought it would be nice if I posted a followup. Here's the solution (code and writeup) I ended up with for any future students :). Paper / Code

  Read the article

• Genetic Programming Online Learning

  - by Lirik

  Has anybody seen a GP implemented with online learning rather than the standard offline learning? I've done some stuff with genetic programs and I simply can't figure out what would be a good way to make the learning process online. Please let me know if you have any ideas, seen any implementations, or have any references that I can look at.

  Read the article

• Is the board game "Go" NP complete?

  - by sharkin

  There are plenty of Chess AI's around, and evidently some are good enough to beat some of the world's greatest players. I've heard that many attempts have been made to write successful AI's for the board game Go, but so far nothing has been conceived beyond average amateur level. Could it be that the task of mathematically calculating the optimal move at any given time in Go is an NP-complete problem?

  Read the article

< Previous Page | 10 11 12 13 14 15 16 17 18 19 20 21  | Next Page >