# Projective simulation for classical learning agents: a comprehensive investigation

arXiv: https://arxiv.org/abs/1305.1578 · HTML: https://mlsanity.com/paper/1305.1578/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2013.

## Built on by (most cited first, 6 of 6)

- [Optimal foraging strategies can be learned](https://mlsanity.com/paper/2303.06050/) (2023)
- [Towards interpretable quantum machine learning via single-photon quantum walks](https://mlsanity.com/paper/2301.13669/) (2023)
- [Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive Bias](https://mlsanity.com/paper/2402.10192/) (2024)
- [Free Energy Projective Simulation (FEPS): Active inference with interpretability](https://mlsanity.com/paper/2411.14991/) (2024)
- [Quantum circuit synthesis of Bell and GHZ states using projective simulation in the NISQ era](https://mlsanity.com/paper/2104.13297/) (2021)
- [Interpreting Quantum Learning Models via Stochastic Processes](https://mlsanity.com/paper/2607.17327/) (2026)

## Abstract (arXiv)

We study the model of projective simulation (PS), a novel approach to artificial intelligence based on stochastic processing of episodic memory which was recently introduced [H.J. Briegel and G. De las Cuevas. Sci. Rep. 2, 400, (2012)]. Here we provide a detailed analysis of the model and examine its performance, including its achievable efficiency, its learning times and the way both properties scale with the problems' dimension. In addition, we situate the PS agent in different learning scenarios, and study its learning abilities. A variety of new scenarios are being considered, thereby demonstrating the model's flexibility. Furthermore, to put the PS scheme in context, we compare its performance with those of Q-learning and learning classifier systems, two popular models in the field of reinforcement learning. It is shown that PS is a competitive artificial intelligence model of unique properties and strengths.