Learning State Representations in Complex Systems with Multimodal Data
arXiv:1811.11067
Abstract
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard dataset for unified comparison. In this work, we present a large-scale dataset and evaluation framework for representation learning for the complex task of landing an airplane. We implement and compare several approaches to representation learning on this dataset in terms of the quality of simple supervised learning tasks and disentanglement scores. The resulting representations can be used for further tasks such as anomaly detection, optimal control, model-based reinforcement learning, and other applications.
arXiv commentFixed references
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- State Representation Learning for Control: An Overview
- Decoupling Dynamics and Reward for Transfer Learning
- Unsupervised state representation learning with robotic priors: a robustness benchmark
- Deep Multimodal Representation Learning from Temporal Data