用可调参数模拟七种心理障碍，发现它们在情绪空间中自组织成特定模式。
A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents
- 通过调节认知评估信号，用单一旋钮控制每种心理障碍的严重程度。
- 所有障碍均呈现剂量-反应的单调变化，且对照组无法复现此现象。
- 发现躁狂与焦虑在情绪空间中镜像对应，适合研究共病机制的研究者关注。
在人工代理中建模心理障碍为计算精神病学提供了测试平台，并揭示情感-控制失衡的机制。以往工作通过手工调整奖励函数诱导一种或两种障碍，事后标注行为并报告单次运行结果。本文将障碍建模重构为在评估引导的PPO代理中对认知评估信号的剂量可控操控，将七种障碍（焦虑、躁狂、强迫检查、抑郁、冲动、成瘾和创伤后应激）分别表示为基于计算精神病学理论的单一旋钮，每种症状由预注册的检测工具测量。在超过一千次运行（10个随机种子，4个对照组，95%置信区间）中，每种障碍均表现出非对照组可复现的等级化、单调剂量-反应关系。此外，三个未预先设定的发现浮现：障碍自发组织为二维情绪空间，躁狂与焦虑镜像对应；移除某个旋钮可缓解奖励扭曲型障碍（躁狂、检查、成瘾），但无法缓解回避型障碍（焦虑、创伤后应激），后者在分级暴露课程下可恢复；两个旋钮同时作用时出现非加性交互，产生可检验的共病预测。抑郁与成瘾旋钮在3D像素环境（MiniWorld）中，使用标准卷积代理且无评估批评者的情况下，仍重现其双分离特征，表明该框架超越网格世界具有泛化能力。
原文摘要 · Abstract (English)
Modelling psychological disorders in artificial agents offers a testbed for computational psychiatry and a lens on affective-control failure modes. Prior work induces one or two disorders by hand-tuned reward shaping, labels the behaviour post hoc, and reports single runs. We recast disorder modelling as dose-controllable manipulation of cognitive appraisal signals in an appraisal-guided PPO agent, expressing seven disorders (anxiety, mania, obsessive-compulsive checking, depression, impulsivity, addiction, and post-traumatic stress) each as a single knob grounded in a computational psychiatry account, with each symptom measured by a preregistered assay. Across more than a thousand runs (10 seeds, four controls, 95% confidence intervals) every disorder shows a graded, monotone dose-response that no control reproduces. Beyond these induced effects, three findings emerge that were not written into the reward: disorders self-organise into a two-dimensional affective space in which mania mirrors anxiety; removing a knob remits reward-distortion disorders (mania, checking, addiction) but not avoidance disorders (anxiety, PTSD), which recover under a graded exposure curriculum; and two simultaneous knobs interact nonadditively, yielding testable comorbidity predictions. The depression and addiction knobs further reproduce their double dissociation in a 3D pixel environment (MiniWorld) with a standard convolutional agent and no appraisal critic, showing the framework generalises beyond grid worlds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。