2022 Developer Survey is open! Take survey.
22 votes
Accepted

How to define states in reinforcement learning?

The problem of state representation in Reinforcement Learning (RL) is similar to problems of feature representation, feature selection and feature engineering in supervised or unsupervised learning. ...
user avatar
  • 23.2k
18 votes
Accepted

Why does the policy network in AlphaZero work?

The output of the policy network is as described in the original paper: A move in chess may be described in two parts: selecting the piece to move, and then selecting among the legal moves for ...
user avatar
  • 23.2k
16 votes

How do I keep track of already visited states in breadth-first search?

Dennis Soemers' answer is correct: you should use a HashSet or a similar structure to keep track of visited states in BFS Graph Search. However, it doesn't quite answer your question. You're right, ...
user avatar
12 votes
Accepted

How should I encode the structure of a neural network into a genome?

Section 4.2 of "Essentials of Metaheuristics" has a wealth of information on alternative ways of encoding graph structures via Genetic Algorithms. With particular regard to evolving ANNs, I would ...
user avatar
9 votes

How do I create an AI for a two-players board game?

Assuming it is a turn-based game and, for each turn, there's an optimal choice that will lead to the winning state (zero-sum), you can basically simplify the question to "What is the optimal sequences ...
user avatar
  • 164
9 votes

How to define states in reinforcement learning?

A common early approach to modeling complex problems was discretization. At a basic level, this is splitting a complex and continuous space into a grid. Then you can use any of the classic RL ...
user avatar
8 votes

Can the English language ever be generalized using a set of grammar rules?

Can there ever be a functionally complete set of grammar rules which can parse any statement in English (locale-specific) accurately and which can be possibly implemented for use in AI-based projects? ...
user avatar
  • 575
8 votes
Accepted

How do I keep track of already visited states in breadth-first search?

You can use a set (in the mathematical sense of the word, i.e. a collection that cannot contain duplicates) to store states that you have already seen. The ...
user avatar
  • 9,326
8 votes

How do I keep track of already visited states in breadth-first search?

While the answers given are generally true, a BFS in the 15-puzzle is not only quite feasible, it was done in 2005! The paper that describes the approach can be found here: http://www.aaai.org/Papers/...
user avatar
  • 351
8 votes

Is Nassim Taleb right about AI not being able to accurately predict certain types of distributions?

Yes and no! There's no inherent reason that machine learning systems can't deal with extreme events. As a simple version, you can learn the parameters of a Weibull distribution, or another extreme ...
user avatar
7 votes
Accepted

Given enough computational resources, do we currently have any algorithms which could achieve AI?

What 'infinite' means here could possibly be debated at some length, but that notwithstanding, here are two conflicting answers: 'Yes': Simulate all possible universes. Stop when you get to one ...
user avatar
7 votes
Accepted

How to turn a ternary constraint into three binary constraints?

Let $D_a$ be the domain for A, and $a_i$ the elements of $D_a$. Let $D_b$ and $D_c$ work similarly for $B$ and $C$ respectively. We introduce $D_t = \{t | t = (c_i - b_j, c_i)\}$ for all $c_i$ in $...
user avatar
  • 186
7 votes
Accepted

When should I use Reinforcement Learning vs PID Control?

I think the comments are basically on the right track. PID controllers are useful for finding optimal policies in continuous dynamical systems, and often these domains are also used as benchmarks for ...
user avatar
6 votes

Are there any ongoing projects which use the Stack Exchange for machine learning?

There certainly appear to have been research projects involving some form of text mining / information retrieval /etc. and StackExchange sites. Some examples I was able to find through google/google ...
user avatar
  • 9,326
6 votes
Accepted

Is there a trade-off between flexibility and efficiency?

The cleanest result we have on this issue is the "no free lunch" theorem. Basically, in order to make a system perform better at a specific task, you have to degrade its performance on other tasks, ...
user avatar
6 votes

Do I need classification or regression to predict the availability of a user given some features?

Yes. For instance, the popular softmax regression gives you probability distribution for each class. Yes. Softmax is a regression over a set of discrete classes. We can use regression for ...
user avatar
  • 1,368
6 votes

Is analogy necessary to artificial general intelligence?

I don't think I can give you a true answer to the actual question as posed, as I don't have a strict definition of "general intelligence". Nor do I have a solid definition of "critical&...
user avatar
  • 3,679
5 votes

Is there a trade-off between flexibility and efficiency?

As Matthew Graves explained in another answer No free lunch theorem confirms the flexibility - efficiency trade-off. However, this theorem is describing a situation where you have a set of completely ...
user avatar
5 votes

How important is true randomness in AI designs?

Randomness is typically the best one can do with ignorance, rather than a source of strength in its own right. For example, the primary use of randomness in statistics is random assignment (A/B ...
user avatar
5 votes
Accepted

Why is AI safety so much harder than Isaac Asimov's "Three Laws of Robotics"?

The reason this is hard is because it is not trivial to understand what a law means. Many humans still have a hard time understanding laws and thus we have millions of judges and lawyers who study ...
user avatar
5 votes
Accepted

Will we be able to build an artificial intelligence that feels empathy?

Let us describe a very simple system that does something we could label as empathyc. A chatbot answers "I am sorry to hear that. What happened?" when we type "I feel bad", and it replies "I am glad ...
user avatar
5 votes
Accepted

Why do we need both the validation set and test set?

The difference between the validation and test set in my opinion should be explained in this way: the validation set is meant to be used multiple times. the test set is meant to be used only once. ...
user avatar
4 votes

How should I encode the structure of a neural network into a genome?

Using evolutionary algorithms to evolve neural networks is called neuroevolution. Some neuroevolution algorithms optimize only the weights of a neural network with fixed topology. That sounds not ...
user avatar
4 votes

What technologies are needed for a self-driving car?

You're going to need some way to 'see' the area around the car, and to track the speed of nearby objects. Google uses a combination of LIDAR, radar, conventional cameras, and occasionally sonar (see ...
user avatar
  • 410
4 votes

Given enough computational resources, do we currently have any algorithms which could achieve AI?

We're definitely nowhere near that level of AI; at best, high-tech solutions like deep convolutional neural nets can help with image recognition and some other algorithms can perform things like ...
user avatar
4 votes

Are there real applications of fuzzy logic?

You've obviously never heard of fuzzy logic washing machines. ● Typically, fuzzy logic controls the washing process, water intake,water temperature, wash time, rinse performance, and spin speed. ...
user avatar
4 votes
Accepted

What approach should I use to detect faces in video game footage?

At first, you can find lots of information as pedestrian detection. As you are trying to localize game characters, the face is not the best option. You need to look for the character in general. ...
user avatar
4 votes
Accepted

How should I represent the input to a neural network for the games of tic-tac-toe, checkers or chess?

When you are working with neural networks, as long as the data is there, the neural network is usually able to learn how to process it into a useful result. However, you usually also want to keep the ...
user avatar
4 votes
Accepted

Are Neural Net architectures accidental discoveries?

Although there is a strong element of "try and see" that has driven successful architectures, the drivers for what to try are often inspired by underlying theory or knowledge from other disciplines. ...
user avatar
  • 23.2k

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