# Split Q Learning: Reinforcement Learning with Two-Stream Rewards

## TL;DR

This paper introduces Split Q Learning, a reinforcement learning framework that models two-stream reward processing inspired by human neurological conditions, enabling better understanding of complex decision-making and behavioral abnormalities.

## Contribution

It presents a novel two-stream reward processing framework for reinforcement learning, inspired by neurological and psychiatric conditions, extending standard Q-learning.

## Key findings

- Framework models reward biases associated with neurological conditions
- Enables analysis of multi-agent interactions in socioeconomic systems
- Provides a basis for unified behavioral modeling across mental conditions

## Abstract

Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems. Moreover, from the behavioral modeling perspective, our parametric framework can be viewed as a first step towards a unifying computational model capturing reward processing abnormalities across multiple mental conditions and user preferences in long-term recommendation systems.