Interpretable experiential learning based on state history and global feedback

TL;DR

This paper introduces an interpretable experiential learning model that uses state history and global feedback to learn transition graphs, showing competitive performance on Atari benchmarks.

Contribution

It presents a novel, interpretable model for reinforcement learning based on state transitions and global feedback, suitable for resource-limited settings.

Findings

Achieved performance comparable to neural network solutions on Atari Breakout.

Developed a transition graph model with utility and evidence counts.

Demonstrated the model's applicability to resource-constrained environments.

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.