Upside-Down Reinforcement Learning for More Interpretable Optimal Control

TL;DR

This paper explores using tree-based methods in Upside-Down Reinforcement Learning to enhance interpretability while maintaining performance across control benchmarks.

Contribution

It demonstrates that non-neural network algorithms like Random Forests can effectively implement UDRL, offering more interpretable policies.

Findings

Tree-based methods perform comparably to neural networks in UDRL tasks.

Policies derived from tree-based methods are inherently more interpretable.

The approach enhances transparency and robustness in reinforcement learning.

Abstract

Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-Based algorithms instead, aim to learn an approximation of the underlying model of the RL environment and then use it in combination with planning algorithms. Upside-Down Reinforcement Learning (UDRL) is a novel learning paradigm that aims to learn how to predict actions from states and desired commands. This task is formulated as a Supervised Learning problem and has successfully been tackled by Neural Networks (NNs). In this paper, we investigate whether function approximation algorithms other than NNs can also be used within a UDRL framework. Our experiments, performed over several popular optimal control benchmarks, show that tree-based methods like Random Forests and Extremely Randomized Trees can perform just as well as NNs with the significant benefit of resulting in policies that are inherently more interpretable than NNs, therefore paving the way for more transparent, safe, and robust RL.