Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning

TL;DR

This paper introduces an expert-guided symmetry detection method for data augmentation in offline reinforcement learning, improving model accuracy and policy performance in both deterministic and non-deterministic environments.

Contribution

It extends symmetry detection techniques to non-deterministic MDPs and proposes a statistical threshold for categorical environments, enhancing offline RL performance.

Findings

Data augmentation reduces distributional shift in learned models

Performance improves when applying policies trained on augmented data

Method effective in both deterministic and non-deterministic MDPs

Abstract

Offline estimation of the dynamical model of a Markov Decision Process (MDP) is a non-trivial task that greatly depends on the data available in the learning phase. Sometimes the dynamics of the model is invariant with respect to some transformations of the current state and action. Recent works showed that an expert-guided pipeline relying on Density Estimation methods as Deep Neural Network based Normalizing Flows effectively detects this structure in deterministic environments, both categorical and continuous-valued. The acquired knowledge can be exploited to augment the original data set, leading eventually to a reduction in the distributional shift between the true and the learned model. Such data augmentation technique can be exploited as a preliminary process to be executed before adopting an Offline Reinforcement Learning architecture, increasing its performance. In this work we extend the paradigm to also tackle non-deterministic MDPs, in particular, 1) we propose a detection threshold in categorical environments based on statistical distances, and 2) we show that the former results lead to a performance improvement when solving the learned MDP and then applying the optimized policy in the real environment.