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

arXiv: https://arxiv.org/abs/2112.09943 · HTML: https://mlsanity.com/paper/2112.09943/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 18 Dec 2021.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 12 of 12)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models](https://mlsanity.com/paper/1810.01367/) (2018)
- [MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning](https://mlsanity.com/paper/2006.16908/) (2020)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Plannable Approximations to MDP Homomorphisms: Equivariance under Actions](https://mlsanity.com/paper/2002.11963/) (2020)
- [Expert-Guided Symmetry Detection in Markov Decision Processes](https://mlsanity.com/paper/2111.10297/) (2021)
- [Offline Learning for Planning: A Summary](https://mlsanity.com/paper/2010.01931/) (2020)

## Built on by (most cited first, 1 of 1)

- [Deep deterministic policy gradient with symmetric data augmentation for lateral attitude tracking control of a fixed-wing aircraft](https://mlsanity.com/paper/2407.11077/) (2024)

## Abstract (arXiv)

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.