1 year, 5 months ago

First semester project for the Interactive Machine Learning 2022/2023 course at MIM UW

This is the first semester project for the Interactive Machine Learning 2022/2023 course at MIM UW. The task is to choose optimal batches of queries for training a model for predicting frags in a video game Tactical Troops: Anthracite Shift.

Overview

The goal of this competition is to choose two subsets of samples from the data pool such that they bring the largest improvement to a prediction model. 

Competition rules are given in Terms and Conditions.

The description of the task, data, and evaluation metric is in the Task description section. 

The deadline for submitting solutions is April 30, 2023

Terms & Conditions
 
 
Please log in to the system!
Rank Team Name Is Report   Preliminary Score Final Score Submissions
1
mgrotkowski
True True 3.6270 3.601400 35
2
Mateusz Błajda
True True 3.6182 3.594500 17
3
jandziuba
True True 3.6377 3.593700 25
4
lastmanstanding
True True 3.6287 3.590700 44
5
MJ
True True 3.6444 3.590000 45
6
Krzysztof Jankowski
True True 3.6209 3.588400 20
7
Karol
True True 3.6174 3.581500 28
8
baseline
True True 3.6040 3.580000 7
9
basiekjusz
True True 3.5994 3.575700 10
10
ggruza
True True 3.6100 3.573100 25
11
kuba
True True 3.6109 3.570600 10

The task in this project is to choose two subsets of samples from the data pool such that they bring the largest improvement to a prediction model. The size of subsets should be 50, 200, respectively. 

The initial batch of samples and the data pool are given as csv files. Keep in mind that the rows are indexed from 1 (not 0).

Each row in the data corresponds to a preprocessed representation of a game state. The task is to predict whether in this game turn the moving player will score a frag.

Format of submissions: solutions should be submitted as text files with two lines. The first line should contain exactly 50 integers - the indices of samples from the data pool (samples are indexed starting from 1), separated by commas. The second line should contain analogous indices for the second set of samples, with 200 integers.

Evaluation: the evaluation of submitted solutions will be done using an XGBoost model, trained independently on the three sets of samples added to the initial data which was made batch available to participants. Each model will be evaluated on a separate test set (hidden from participants). The quality metric used for the evaluation will be the average AUC. Results for the two sample sets will be averaged with weights 4 and 1 for the subset size 50 and 200, respectively.

During the challenge, your solutions will be evaluated on a fraction of the test set, and your best preliminary score will be displayed on the public Leaderboard. After the end of the competition, the selected solutions will be evaluated on the remaining part of the test data and this result will be used for the evaluation of the project.

This forum is for all users to discuss matters related to the competition. Good manners apply!
  Discussion Author Replies Last post
Indexing start Mateusz 0 by Mateusz
Friday, May 05, 2023, 19:24:49