English

Interpretable experiential learning based on state history and global feedback

Machine Learning 2026-05-05 v1 Artificial Intelligence

Abstract

A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model represented by a transition graph between sets of states, with transitions attributed with utility and evidence count. This model is expected to be suitable for solving reinforcement learning problem in resource-constrained environments. The model was thoroughly evaluated on the OpenAI Gym Atari Breakout benchmark, demonstrating performance comparable to some known neural network-based solutions.

Keywords

Cite

@article{arxiv.2605.00940,
  title  = {Interpretable experiential learning based on state history and global feedback},
  author = {Anton Kolonin},
  journal= {arXiv preprint arXiv:2605.00940},
  year   = {2026}
}

Comments

5 figures

R2 v1 2026-07-01T12:45:43.303Z