Emergence of addictive behaviors in reinforcement learning agents

Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir

Research output: Contribution to journalConference articlepeer-review


This paper presents a novel approach to the technical analysis of wireheading in intelligent agents. Inspired by the natural analogues of wireheading and their prevalent manifestations, we propose the modeling of such phenomenon in Reinforcement Learning (RL) agents as psychological disorders. In a preliminary step towards evaluating this proposal, we study the feasibility and dynamics of emergent addictive policies in Q-learning agents in the tractable environment of the game of Snake. We consider a slightly modified version of this game, in which the environment provides a “drug” seed alongside the original “healthy” seed for the consumption of the snake. We adopt and extend an RL-based model of natural addiction to Q-learning agents in these settings, and derive sufficient parametric conditions for the emergence of addictive behaviors in such agents. Furthermore, we evaluate our theoretical analysis with three sets of simulation-based experiments. The results demonstrate the feasibility of addictive wireheading in RL agents, and provide promising venues of further research on the psychopathological modeling of complex AI safety problems.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
StatePublished - 2019
Event2019 AAAI Workshop on Artificial Intelligence Safety, SafeAI 2019 - Honolulu, United States
Duration: Jan 27 2019 → …

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Emergence of addictive behaviors in reinforcement learning agents'. Together they form a unique fingerprint.

Cite this