# A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents

arXiv: https://arxiv.org/abs/2607.07753 · HTML: https://mlsanity.com/paper/2607.07753/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 5 of 5)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Emotion in Reinforcement Learning Agents and Robots: A Survey](https://mlsanity.com/paper/1705.05172/) (2017)
- [Appraisal-Guided Proximal Policy Optimization: Modeling Psychological Disorders in Dynamic Grid World](https://mlsanity.com/paper/2407.20383/) (2024)

## Abstract (arXiv)

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.