Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [game]

Questions related to analysing or optimising games, such as board games, card games or video games.

Simple games such as tic-tac-toe (noughts and crosses) can make interesting and practical toy problems to apply a variety of data analysis. More complex games can challenge state of the art algorithms and are areas on ongoing research.

Artificial intelligence that seeks to optimise game play may or may not be related to data science.

Most likely to be on topic are questions about markov models, bandit algorithms and reinforcement learning. Reinforcement learning specifically is a machine learning approach where analysis or optimal play can be discovered through observing outcomes of actions taken in a game, without prior knowledge of how the game is supposed to behave or be played.

Probably off-topic are questions about designing games, implementing game rules in software, "traditional AI" search algorithms such as A*.

23 questions
8
votes
1 answer

Which ML approach to choose for the game AI when rewards are delayed?

Question: Which Machine Learning approach should I choose for the AI of my computer game, where the actions of the AI do not lead to immediate rewards, but delayed rewards instead? About me: I am a complete beginner in the area of machine learning.…
Logende
  • 61
  • 4
3
votes
1 answer

Supervised learning for a turn-based game?

So I have 4GB of turn-by-turn data for many games of a particular strategy game. It appears that most people interested in using ML to build an AI for turn-based games use reinforcement learning to build a model on the fly. Since I already have…
user6118986
  • 131
  • 2
2
votes
0 answers

Which one of these is the most efficient way to model training data for a neural network that will play a snake-like game?

I am building an AI using a neural network that will play Tron against a human player. The game consists of a board with fixed width and height where each player can move at any direction (except for the oposite direction he is facing). Each…
Tesserato
  • 41
  • 1
2
votes
0 answers

CNN combined with a competitive search algorithm

I'm reading some papers about Deep Neural Networks applied for board games, like for Go with AlphaGo, AlphaGo Zero and some other games, like Othello and Chess. Most of the works are using CNN's as a direct move predictor. I want to make some…
Matheus Prandini
  • 107
  • 6
2
votes
2 answers

How to optimize for time correlated hidden function - the magical candy machine

Let's assume that we have this magical candy machine which takes candies as input and delivers again candies as output. For any given time t, it picks a random function which is strictly increasing up to a point such as f(2) = 6 here, and then it…
metdos
  • 131
  • 5
2
votes
1 answer

ML that learns to predict and play a simple wagering game

I have a simple game I'm building for fun, just to see how well ML can work with simple data sets. Basically it's just a game where it has turns that go like this: Computer generates a random number $x$, and does not show the player. Player wagers…
JDOE
  • 31
  • 3
2
votes
0 answers

Evaluate the result of a Zero-sum game

I'm currently working on an AI playing Mandarin using Minimax. I can extract this dictionary from a game where 2 AI with different depth plays with each other: game_result = { "winner": winner, # 1, 2 for player 1 and 2 respectively …
vcth4nh
  • 21
  • 1
2
votes
4 answers

Which AI algorithm is best for chess?

I'm working on my chess bot, and I would like to implement simple artificial intelligence for it. I'm new in it, so I'm unsure how to do it specifically on chess. I heard about Q-learning, Supervised/Unsupervised learning, Genetic algorithm, etc.,…
Jenia
  • 129
  • 1
  • 4
2
votes
1 answer

Learning a board game using a genetic neural network

I've never really done any practical machine learning, this is just a hobby for me. I'm trying to create a process using a neural network to learn the board game "7 Wonders." Here's how I want this experiment to be done: Take all inputs (I've…
user1005909
  • 121
  • 2
1
vote
1 answer

Predicting outcome of MOBA team games

MOBA team games have teams composed of a subset of 5 heroes from a larger set of possible heroes (say 100 heroes in the larger set) For example, a game can be between a team with heroes 1,8,43,65 and 71 and a team with heroes 3,7,23,41 and 45. What…
Aviad P.
  • 111
  • 2
1
vote
0 answers

Feature Encoding for team based sports data

I am currently playing around with Keras and try to use it with various datasets. Now I have a small datasets of football game results. date, home_team, away_team, goals_home_team, goals_away_team Predicting the goals is probably too hard so I…
Martin Pichler
  • 19
  • 1
1
vote
2 answers

In generative adversarial models (GANs), why should we solve min-max problem and not max-min?

I know that in GANs model, there is min-max game between generator and discriminator which discriminator tries to maximize the loss function and the goal of generator is to minimize it. But why we write the loss function as min-max problem and not…
user137927
  • 379
  • 1
  • 3
  • 10
1
vote
0 answers

What kind of neural network would work best for loosely-defined data, like video game RAM?

I'm trying to build out a network layer map for a neural network to use in an NES AI. Most networks I run across on web searches are CNNs that use image data to identify things. Miles and miles and miles of papers, questions, and tutorials about…
SineSwiper
  • 111
  • 1
1
vote
0 answers

comparison of linear Q-learning and DQN

I saw in DQN nature paper 2015 https://www.nature.com/articles/nature14236(Extended Data Table 4) some comparisons between DQN and linear Q-learning. The ratio of reward for different games are very different. For instance I saw the ratio of…
user10296606
  • 1,784
  • 5
  • 17
  • 31
1
vote
2 answers

Can AlphaGo Zero adapt to oponents skills/profile?

I read the AlphaGo Zero paper and I didn't found nothing about it in there. But I would like to know if AlphaGo Zero can adapt to the way the oponent plays (oponent profile) or something like this. Thanks!!
Matheus Prandini
  • 107
  • 6
1
2