Interpretable experiential learning based on state history and global feedback
It offers an interpretable alternative to black-box reinforcement learning models for resource-constrained environments.
The paper introduces an interpretable experiential learning model that learns a transition graph with utility and evidence counts, achieving performance comparable to neural network-based methods on the Atari Breakout benchmark.
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.