Projective simulation for classical learning agents: a comprehensive investigation Mautner, Julian Manzano Diosdado, Daniel Inteligencia artificial Artificial intelligence We study the model of projective simulation (PS), a novel approach to arti cial intelligence based on stochastic processing of episodic memory which was recently introduced [1]. Here we provide a detailed analysis of the model and examine its performance, including its achievable e ciency, its learning times and the way both properties scale with the problems' dimension. In addition, we situate the PS agent in di erent learning scenarios, and study its learning abilities. A variety of new scenarios are being considered, thereby demonstrating the model's exibility. Further more, to put the PS scheme in context, we compare its performance with those of Q-learning and learning classi er systems, two popular models in the eld of reinforcement learning. It is shown that PS is a competitive arti cial intelligence model of unique properties and strengths. 2022-11-16T08:39:21Z 2022-11-16T08:39:21Z 2014-12-01 journal article Published version: Mautner, J... [et al.]. Projective Simulation for Classical Learning Agents: A Comprehensive Investigation. New Gener. Comput. 33, 69–114 (2015). [https://doi.org/10.1007/s00354-015-0102-0] https://hdl.handle.net/10481/77989 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Springer