This repository contains data collected during multiple tests of the Scorca agent.
This data was used to generate the various plots seen in the ICAART paper titled Knowledge Modelling, Strategy Designing, and Agent Engineering for Reconnaissance Blind Chess, and to forge decisions for the agent, i.e. with which strategy to go and which hyperparameters to use.
It also contains multiple scripts used to generate the plots in the paper.
The project is organized into several key directories, each containing specific components of the Scorca agent's testing and data analysis:
/experiments: Contains various experimental data and scripts./entropy_comp: Data and scripts related to entropy computation experiments./piece_states_removal: Information on experiments involving the removal of piece states./sense_comp: Contains sub-directories for adapted entropy, likely senses, and opponent move weight analysis.
/misc_src: Miscellaneous source files and scripts./efficiency: Scripts and data related to the efficiency analysis of the agent./enemy_bot_movement: Data on enemy bot movement patterns and strategies./history: Historical data and analysis scripts./naive_entropy: Scripts for naive entropy calculations.
/sense_comp: Sense computation related files./all_possible_states: Tracking and analysis of all possible board states./likely_senses: Data on the most likely senses used in various game scenarios./opp_move_weight: Analysis of opponent move weight in different contexts.
For the agent source code, please refer to the Scorca repository.
- Contact Robin in case of any inquiry (rb.stoehr@gmail.com)
- The licence is CC-BY 4.0.