Questions tagged [artificial-intelligence]

Questions about design and properties of agents that act in a dynamic environment and make decisions towards some goal without user control.

Filter by
Sorted by
Tagged with
3
votes
1answer
939 views

Closed form solution for a single layer linear perceptron

Let f be a one-layer neural network which is linear (ie. no activation function). Let it have $p$ inputs and $q$ outputs. These are fully connected by weights $W$. We have $n$ inputs $x \in \mathbb{R}^...
3
votes
1answer
369 views

Why does ε-greedy $Q$-learning not oscillate?

I have a intuitive question on the convergence of $Q$- learning. In $Q$ learning for each step a $Q$- value is learned for the state-action pair where the action is selected according to the $\epsilon$...
3
votes
2answers
2k views

Q-learning in a Dynamic environment

I am new to reinforcement learning. Lately, I have learned Q-learning using the following tutorial. Is Q-learning still possible if the environment is dynamic. Using the environment of the tutorial ...
3
votes
1answer
74 views

How do you protect an AI from a human doing “illogical” moves?

Using a monte carlo approach and evalutation function. Some moves will deemed to be more advantageous than others. As a computer plays itself, it will generally go for the best moves possible. And ...
3
votes
1answer
86 views

Confusion regarding terminology surrounding perceptron learning

I am having trouble understanding the terminology with perceptron learning. Is my current understanding correct? Let's say I have some data that classifies what type of flower a particular flower is. ...
3
votes
1answer
93 views

What is the name of this problem in Computer Vision?

My google skills have failed me during research for a college project. Our task is write a program that describes an image in spacial terms, e.g. "Cat on the left of a chair", or for a simple image "...
3
votes
1answer
593 views

Clarification on Tabu Search

I need some help in understanding the 'Tabu Search' Algorithm. (Wikipedia) I miss a simple explanation to Tabu Search. Anyway, I'm trying to refer to available resources and build an understanding. ...
3
votes
1answer
635 views

Identifying an object in an image based on color (AI ?)

First off, I am not sure if this is the correct stackexchange site to ask this question on, so moderators can feel free to move it. I am working on an application that identifies an object in an ...
3
votes
1answer
106 views

Comparing variations of A*

I am running some experiments with a maze, and trying different variations of A*. Based on my experiments, I have been able to form some opinion (that at least in those cases, graph checking is better ...
3
votes
2answers
552 views

Show that the Turing Machine domain can be viewed as a classical planning domain

This is one of my assignments. I am not able to comprehend how to reduce the Turing machine domain to Classical planning domain. My understanding is that we have to essentially perform complexity ...
3
votes
1answer
826 views

'Texas Hold Em Poker' Agent Heuristics to help decide whether to fold or bet?

I am designing a poker agent with different heuristics to decide whether to raise, fold or pass (in Texas holdem poker). I am planning to have 4 heuristics with the agent biased to one of them. The ...
3
votes
1answer
145 views

Can bottom-up architectures be effectively programmed in top-down paradigms?

The subsumption architecture, proposed by Rodney Brooks in 1986, is a "bottom-up" approach, in which robots are designed using simple hierarchical models. These models build upon and subsume the ...
3
votes
2answers
35 views

How do you prove a heuristic is admissible?

How does one prove that a suggested heuristic is admissible? Is this even possible? For Example: Let's say I have the game Free Cell. Rules: https://en.wikipedia.org/wiki/FreeCell How can I ...
3
votes
1answer
48 views

Neural net that alters its own parameters

Is it possible for an AI neural net to be able to modify its own parameters/hyperparameters and/or add new parameters/hyperparameters? If so, how has it been implemented? For example, to simulate a ...
3
votes
4answers
981 views

Efficiently labelling training data in machine learning

Obviously it always depends on the specific case. However, my question is how to label data efficiently without writing a source code from scratch which solves the final problem itself? For example, ...
3
votes
1answer
451 views

How many possible policies in a Markov Decision Process?

If a policy yields an action for a state, how come a 3-state MDP with 2 possible actions, i.e. $S = \{Hot, Mild, Cold\}$, $A = \{East, West\}$, has 8 possible policies? Isn't it 6 if there are 2 ...
3
votes
1answer
218 views

Use machine learning algorithms data structure to store information (memory)

DISCLAIMER : I'm pretty new to machine learning field, so forgive me if my questions are somehow naive ... I already searched on Internet about this topic and find nothing interesting so I am ...
3
votes
2answers
89 views

Symmetry in Pattern Databases

I am trying to understand the use of symmetry in pattern databases (Heuristics, single agent search). This is too specialized of a topic to find common videos or explanations in general. I read the ...
3
votes
1answer
822 views

What category of AI would a 2048 bot be considered?

I have just delved into the realm of AI and from what I can tell its a very vast field of study. I am a game programmer, so AI in games is particularly interesting to me. My question is, what type of ...
3
votes
2answers
1k views

Can an artificial neural network convert from cartesian coordinates to polar coordinates?

Given cartesian coordinates $x$ and $y$ as input, can a neural network output $r$ and $\theta$, the equivalent polar coordinates? This would seem to require an approximation of the pythagorean ...
3
votes
1answer
1k views

the meaning of heuristics in artificial intelligence

I would like to know what 'heuristics' actually means in artificial intelligence. For example, I am reading a paper by Engelbrecht on the convergence analysis of the particles of the algorithm. The ...
3
votes
1answer
137 views

How to validate a connect X game (Tick-Tak-Toe,Gomoku,…)?

Currently I am working on a Gomoku AI (or generally Connect-X games). Implementing the search tree was no problem, but then I got to the point where I had to implement the value function and was ...
3
votes
1answer
271 views

Effective AI for one player-one ghost pacman

I am thinking of a modified version of pacman. In this version, it will be a two-player game. Each player will have one pacman and one ghost. So there are 2 pacmans and 2 ghosts in the board at a time....
3
votes
1answer
468 views

Can you solve 3D Tic Tac Toe with Minimax?

I have implemented a 3d Tic Tac Toe game with AI, where the computer is unbeatable. The only thing is that the board looks like this: _ _ _ _ _ _ _ _ rather ...
3
votes
1answer
665 views

How is the environment designed for testing a reinforcement learning algorithm?

I'm working on a project, and have a candidate algorithm which I'd like to test. Before I go any further, I need to get the hang of how to code the "structure" of the environment in which my system is ...
3
votes
2answers
273 views

Adversarial Monte Carlo Tree Search Asymmetry

Monte Carlo Tree Search with UCT is praised for it's asymmetric tree growth, growing promising subtrees more than non-promising ones. But in a 2-player adversarial game, when a win at one node is a ...
3
votes
1answer
317 views

Who coined the term “artificial intelligence”?

The most obvious (and commonly given) answer to this question is John McCarthy, but I have traced the first usage of this term to a 1955 paper, which McCarthy co-authored with Marvin Minsky, Nathaniel ...
3
votes
1answer
184 views

Using the appropriate machine learning algorithm [duplicate]

I am not sure if this is the right forum to ask this. I have some data of the houses, like their size(in square meters), if they use aircondition, how many residents live in, I have their electricity ...
3
votes
1answer
321 views

Can Real-Time Strategy games be ever solved?

With the advent of BWAPI, many AI enthusiasts have been making amazing AIs that can compete against top players in Starcraft. This led me to wonder if RTS (Real-Time Strategy) games can ever be solved ...
3
votes
0answers
76 views

Was there a phase in Machine Learning timeline when researchers thought some Neural Networks could not be trained?

I was talking to a professor who made a comment to my question. Me: So much of quality literature around this topic ( IP Protection for Neural Weights) emanated in 1990-1991, I'm truly at loss ...
3
votes
0answers
135 views

Is “expert system” now an obsolete/unpopular term?

While doing research on expert systems, I notice that it is rare to see this term used in the last 20 years. For example, a recent paper was: Wang, Hao, Naiyan Wang, and Dit-Yan Yeung. "Collaborative ...
3
votes
0answers
118 views

A case study for search techniques in AI

We are teaching an artificial intelligence class and we need a different case study other than geographical maps (the popular example is the map of Romania) to explain the difference between Breadth-...
3
votes
0answers
22 views

proof that STRIPS terminates

I was reading page 6 of https://www.cs.cmu.edu/~reids/planning/handouts/Linear.pdf And it is not clear to me that the STRIPS algorithm necessarily terminates. Namely if we have a simple goal sg on ...
3
votes
0answers
615 views

Estimating size of state space

I have been studying search problems in AI, and I am having some troubles understanding some points in these concepts: State Space: "represents the environment of the problem, the set of all states ...
3
votes
0answers
76 views

Is there a reduction concept in artitificial intelligence?

Is there a concept for comparing algorithms in artificial intelligence theory similar to reduction in complexity theory (Wikipedia)? I'm asking this because I was wondering how AI algorithms are to ...
3
votes
0answers
100 views

What are the theoretical and practical contributions of Multiagent Systems to science?

Speaking about multiagent systems (MAS) is about as fuzzy as talking about artificial intelligence systems (AI). They are in essence the distributed counterpart of AI. While there are no so-called "...
3
votes
0answers
98 views

Limited lookahead pathfinding strategies on infinite graphs

I'm new to pathfinding algorithms and trying to find a good or even optimal heuristic for the following problem: Say you have a 3D square-lattice cuboid graph with randomly removed edges (with ...
3
votes
0answers
265 views

Prerequisites for AI and machine learning [closed]

I am interested in the field of AI and machine learning and I am fairly good at mathematics and statistics and programming in general. However I lack a formal CS education and my undergraduate degree ...
3
votes
0answers
106 views

Why isn't there a big HTM machine already?

I've been reading a bit about Hierarchical Temporal Memory and Memory Prediction. I found a great paper: How the brain might work: A hierarchical and temporal model for learning and recognition, ...
3
votes
1answer
555 views

MGU and Variable Standardization - CNF

I have been reading on converting first order logic sentences to conjunctive normal form, and then performing resolution. One of the steps of converting to CNF, is to Standardize variables: rename ...
3
votes
2answers
323 views

About the behaviour of multi-layer perceptrons

I have a multilayer perceptron. It has an input layer with two neurons, a hidden layer with an arbitrary number of neurons, and an output layer with two neurons. Given that ...
3
votes
1answer
387 views

How to tell if a Heuristic is monotonic

I've applied a Heuristic to a puzzle where I need to move all off the B's the the right of the W's. my Heuristic is the total distance of the B's from the right most W's. my initial state is (B,B,B,*,...
2
votes
1answer
531 views

In principle, what is the relation between Artifical Intelligence and Turing machine?

I am working on my cs project about AI & Turing machines, so i know that Artifical Intelligence is meant to implement different algorithms into the machine {the computer} to solve a problem or a ...
2
votes
2answers
1k views

Why does an admissible heuristic mean A* is optimal?

An admissible heuristic never overestimates the cost to reach the goal. However, isn't that only the relative difference between heuristics for two different paths matter? Say we have optimal path A ...
2
votes
1answer
637 views

Is Q-Learning ever better than Brute Force?

I am currently learning about the Q-learning algorithm, so I therefore assume that it has some use or purpose. However I currently cannot see how it is in any way useful. In terms of complexity class, ...
2
votes
2answers
55 views

Does an optimal path imply the heuristic is admissible?

If we are given an A$^*$ path search with some heuristic $h$ that yields an optimal path, without knowing that the heuristic is admissible beforehand, would this imply that $h$ is admissible?
2
votes
1answer
157 views

Recognizing Horn clauses

I am currently studying model theory and I am trying to decide if a clause is a Horn Clause. I know that a Horn Clause is a clause with at most one positive literal, but there are some clauses that it ...
2
votes
1answer
42 views

Is Artificial General Intelligence possible with our current machine learning models? [closed]

In other words, is artificial human level intelligence not possible yet just because of limitations in processing power and amount of data required to train the models? Or we don't have the knowledge ...
2
votes
1answer
94 views

that there would be no perfect strategy for poker

In my opinion, every imperfect information game where there is the possibility of bluffing lacks a perfect (or winning) strategy, for the simple reason that knowing your opponent's strategy will let ...
2
votes
1answer
104 views

Is there a program that will tell you the optimal algorithm for ANY problem if the problem is decidable? [duplicate]

Is there a program that will tell you the optimal algorithm for ANY problem if the problem is decidable? If not, why not? If yes, how can such a program be realistically constructed? I would prefer ...