Agent-Based Reinforcement Learning Model of Burglary (ARLMB) datasets for article: Learning the Rational Choice Perspective: A Reinforcement Learning Approach to Simulating Offender Behaviours in Criminological Agent-Based Models

This data deposit contains synthetically generated crime data from the Agent-Based Reinforcement Learning Model of Burglary developed for the research article: Learning the Rational Choice Perspective:<em> A Reinforcement Learning Approach to Simulating Offender Behaviours in Criminological Agent-Based Models</em> <br> The data directory is as follows: <br> Model/ Data_Analysis__Notebook.ipynb MC1_Data MC2_Data MC3_Data <br> The <strong>Data_Analysis__Notebook.ipynb</strong> is the jupyter notebook used to produce the analysis within the article. This notebook requires <strong>python 3.* </strong>with packages such as <strong>matplotlib, seaborn, numpy, pandas, plotly, scipy</strong> to run. <br> The MC1, MC2 and MC3 folders contain the .txt files containing the data outputs used for analysis in the article. Where MC1 = Experiment Condition 1 in the article. <br> Each column of the data is described as follows: <br> <br> AgentID: A unique agent identifier. Action: The current action an agent has chosen can be one of [OFFEND, DON'T OFFEND, MOVE]. Area: The locality in which the above action has taken place. Target_Attractiveness: The target attractiveness value of the property that has been victimised. Target_Reward: The reward at the property that has been victimised. Target_Risk: The risk surrounding the property that has been victimised. Target_Effort: The effort of the property victimised by the specific offender agent. Total_Cumulative_Reward: The total sum of Target_Attractiveness acquired by the offender agent. xAxisPos: The x-axis position of the cell the offender agent is currently in. zAxisPos: The y-axis position of the cell the offender agent is currently in. Zone_Travelled_To: The locality the offender agent is currently travelling towards. Episode: The current episode. Distance_To_Home: The normalised Euclidean distance to the offender agent's home node from the current victimised target. Distance_To_Next_Node: The normalised Euclidean distance to the next routine activity node from the current victimised target. Timestep: The current discrete time point. Target_Cumulative_Reward: The total amount of Target_Attractiveness the offender agent wants to achieve. <br> <br> <br> <br> <br> <br> <br> <br> <br> <br>

本数据集存档包含为研究论文《理性选择视角学习：面向犯罪学基于智能体模型的犯罪者行为模拟强化学习方法》（Learning the Rational Choice Perspective: A Reinforcement Learning Approach to Simulating Offender Behaviours in Criminological Agent-Based Models）开发的盗窃场景基于智能体的强化学习模型所生成的合成犯罪数据。
数据目录如下：
Model/ Data_Analysis__Notebook.ipynb MC1_Data MC2_Data MC3_Data

**Data_Analysis__Notebook.ipynb** 为用于生成论文分析结果的Jupyter笔记本（Jupyter Notebook），该工具需运行Python 3.*版本环境，并依赖matplotlib、seaborn、numpy、pandas、plotly、scipy等第三方工具包。

MC1、MC2及MC3文件夹内含用于论文分析的文本格式（.txt）数据输出文件，其中MC1对应论文中的实验条件1。

各数据列的含义说明如下：
1. 智能体唯一标识符（AgentID）：用于标识单个智能体的唯一编号。
2. 动作（Action）：智能体当前选择的动作，可选取值为[OFFEND, DON'T OFFEND, MOVE]。
3. 区域（Area）：上述动作实施的所在辖区。
4. 目标吸引力（Target_Attractiveness）：受害房产的目标吸引力数值。
5. 目标收益（Target_Reward）：受害房产所能提供的收益。
6. 目标风险（Target_Risk）：受害房产周边的风险水平。
7. 目标投入成本（Target_Effort）：特定犯罪者智能体实施针对该房产的犯罪所需付出的成本。
8. 累计总收益（Total_Cumulative_Reward）：犯罪者智能体累计获得的目标吸引力总和。
9. X轴坐标（xAxisPos）：犯罪者智能体当前所在单元格的X轴位置。
10. Z轴坐标（zAxisPos）：犯罪者智能体当前所在单元格的Y轴坐标（该字段命名为zAxisPos以匹配原始数据格式）。
11. 前往区域（Zone_Travelled_To）：犯罪者智能体当前正前往的辖区。
12. 实验轮次（Episode）：当前所属的实验轮次。
13. 归一化到家欧氏距离（Distance_To_Home）：当前受害目标到犯罪者智能体家节点的归一化欧氏距离。
14. 归一化到下一节点欧氏距离（Distance_To_Next_Node）：当前受害目标到下一个日常活动节点的归一化欧氏距离。
15. 时间步长（Timestep）：当前离散时间点。
16. 目标累计收益（Target_Cumulative_Reward）：犯罪者智能体期望达成的目标吸引力总数值。