Guardado en:
Detalles Bibliográficos
Autor principal: Kolonin, Anton
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.00940
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917454069891072
author Kolonin, Anton
author_facet Kolonin, Anton
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00940
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Interpretable experiential learning based on state history and global feedback
Kolonin, Anton
Machine Learning
Artificial Intelligence
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.
title Interpretable experiential learning based on state history and global feedback
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.00940