Projective simulation for classical learning agents: a comprehensive investigation
This work provides a comprehensive evaluation of a novel AI model for reinforcement learning agents, though it appears incremental in extending prior research.
The authors investigated the projective simulation (PS) model, a stochastic episodic memory-based AI approach, analyzing its efficiency, learning times, and scalability across various learning scenarios, and found it to be competitive with Q-learning and learning classifier systems in reinforcement learning.
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.