10

I would set up a list of goals for your bot. These could be 'maintain a minimum level of health', 'knock out human player', 'block way to location X', etc. This obviously depends on the domain of your MMO. Then you can use a planner to achieve these goals in the game. You define a set of actions with preconditions and effects, set the current goal, and the ...


9

I think you're coming at your problem slightly wrong... what you're essentially talking about is a belief network. You may want to look into existing Bayesian Learning techniques to get your head around this, but belief networks commonly use the exact scenario you're talking about; using a set of known (or uncertain facts) statements to produce some inferred ...


8

Oliver Mason's answer is great for specific methods and tools to use, but I wanted to pull out a more general principle which was mentioned in a comment. The distinction your friend is making is not one that would be generally recognised. One of my university lecturers defined AI as something like "an artificial system that exhibits behaviour that resembles ...


7

Yes, it is possible. Usually, the noise reduction is done using regular signal processing methods, such as spectral subtraction due to demand for low latency. But, of course, modern methods of deep learning are applicable to this problem. For example, the variational autoencoder is the first that comes to my mind, you can check this project. Another example ...


6

There are several different algorithms that can be used for gradient free neural network training. Some of these algorithms include particle swarm optimization, genetic algorithms, simulated annealing, and several others. Almost any optimization algorithm can be used to train a neural network. Here is an overview of some of the algorithms I listed: Particle ...


6

As I see it, it all comes down to game theory, which can be said to form the foundation of successful decision making, and is particularly useful in a context, such as computing, where all parameters can be defined. (Where it runs into trouble is with the aggregate complexity of the parameters per the combinatorial explosion, although Machine Learning has ...


5

Typically, Monte-Carlo Tree Search (MCTS) actually is the go-to "solution" for such problems with large branching factors. I can understand that "vanilla" MCTS may still have unsatisfactory performance, but there is a plethora of extensions/enhancements available. I don't have experience with the specific game you mentioned (Connect6), but from a quick look ...


5

To perform image recognition you have to find a way to represent an image with certain features. One of the defining characteristics of a good image recognition algorithm are it's ability to detect salient regions, that is, regions which contain the most information There is a lot of attention on deep learning for content-based image classification at the ...


5

Blackjack is usually modelled using Monte Carlo (MC) Methods. There is a lot of literature on MC methods which is interesting on its own right but here is a paper describing how MC is applied to Blackjack. There is also a good description on page 110 of the Introduction to Reinforcement Learning. Good luck!


5

Overlap between AI and "Game AI" Nowadays, if you search for AI online, you will find a lot of material about machine learning, natural language processing, intelligent agents and neural networks. These are not the whole of AI by any means, expecially in a historical context, but they have recently been very successful, there is lots of published ...


4

Don't feel too bad for having gotten it slightly wrong because backpropagation is notoriously difficult to implement [1]. There is a technique called gradient checking, which you can implement to test the correctness of your backpropagation implementation. I would argue that even gradient checking is a little tricky to implement. How does gradient checking ...


4

Yes, there are algorithms that try to predict the next state. Usually this will be a model based algorithm -- this is where the agent tries to make use of a model of the environment to help it learn. I'm not sure on the best resource to learn about this but my go-to recommendation is always the Sutton and Barto book. This paper introduces PlanGAN; the idea ...


3

Machine Learning is a bad fit to this problem. Even simple PRNGs that are not suitable for use in simulators (such as rand()) are varied enough that it is very hard to reverse engineer them statistically using generic techniques - essentially what 90% of ML does is fit a generic model to data statistically by altering parameters. The remaining 10% might do ...


3

Pseudo-random number generators are specifically defined to defeat any form of prediction via 'black box' observation. Certainly, some (e.g. linear congruential) have weaknesses, but you are unlikely to have any success in general in predicting the output of a modern RNG. For devices based on chaotic physical systems (e.g. most national lotteries), there is ...


3

I believe you want a neural network that can predict future values of multiple variables given multiple inputs. This belongs to the general time series forecasting problem. One of the best neural network architectures that can handle this problem is the LSTM, which is a type of Recurrent Neural Network. Their architecture allows them to develop a memory of ...


3

Tabu search uses memory to rule out parts of the neighborhood for local search, allowing the trajectory to typically pass through local optima instead of getting stuck in them.


3

You could parallelize the search by dividing the global space in distinct regions/subsets. Then apply in each region a local search. This way you can search the global space systematically, more exhaustively and perhaps in different ways (e.g by applying a different local search method to each region). Finally you can compare the results and choose the best ...


3

You can train your bot using reinforcement learning (in particular Q-Learning). The most important part of the RL is a reward function. If we want agent to do some thing specific, we must provide rewards to it in such a way that it will achieve our goals. It is thus very important that the reward function accurately indicates the exact behaviour So you ...


3

Due to subjective nature, quantitative evaluation of synthetic images is difficult in general. However, there are metrics like Inception Score or FID score that are used for evaluation of generative models like GANs or VAEs. Technically, it considers two aspects of the generated data: Similarity with training data Diversity within itself Even though such ...


3

Machine learning has been used to automatically learn new optimization/learning algorithms. This task is often known as meta-learning, i.e. you learn to learn, in this case, an optimization algorithm, but note that meta-learning does not just refer to learning optimization algorithms (see this blog post). The blog post Learning to Optimize with Reinforcement ...


2

Model of the car What you want to do is close to one-shot image recognition. You have not 1, but 3-4 examples of each car, but that is still a small amount, especially considering the car looks different from different angles (are you supposed to recognize them from any point of view, including sideways, rear, front, and 45 degrees etc.? maybe you also want ...


2

If the measurements you want from the object aren't too complicated (ie. length of a clearly defined feature), and if you are able to acquire a training dataset of images of the objects similar to what your model will see in your use case (same scale/distance), their bounding boxes and their measurements, a model you could try to implement is a Multi-Task ...


2

Father Ted explains why this is a hard problem. Seriously -- if you have stereo images it should be possible, since that's what we use for depth perception. If you know how far away points x1 and x2 are, then you can measure distance using trigonometry. No neural networks needed, I guess. https://en.wikipedia.org/wiki/Triangulation_(computer_vision)


2

You are mixing up lots of things here. Specifically, you seem to be lacking a basic understanding of artificial neural networks and what they can do (e.g. what type of articifial neural networks are linear classifiers/regressors and which can model non-linear relationships). Therefore, I'd take a step back and start with understanding the basics of AI. The ...


2

For example, from among house size, lot size, age of house and asking price, what formula best predicts selling price? There is no general formula for this. Search for neural network regression and you can get started. The AI technique or any prediction algorithm in general will learn a function that maps from the input feature vector $(x_1, ...,x_n)$, ...


2

This is probably not going to work well as a way to make money. People with far larger budgets, and far more training, are already milking out any money to be made this way. This is probably their day job, and they are good at it. That said, here are some ideas: You do not need or want to use a convolutional network for this. Convolutional networks are ...


2

I'm going to start by trying to restate your problem as I understand it. You have a game which contains weapons. Weapons are characterized by 5 different numbers, which can range over different values (1-5 in your examples?). You have a way to simulate combat involving the two weapons. The combat is random, but can be repeated many times. An average win ...


2

This is called "clustering" , If the network is already trained with data that has similar features as of the "symbols", you can use that network with its last classification layer removed , then run a clustering algorithm like "k-means" on top of the vectors obtained from the last layer of the network.


Only top voted, non community-wiki answers of a minimum length are eligible