# Mutual Information Maximization for Robust Plannable Representations

arXiv: https://arxiv.org/abs/2005.08114 · HTML: https://mlsanity.com/paper/2005.08114/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2020.

## Built on by (most cited first, 7 of 7)

- [Temporal Predictive Coding For Model-Based Planning In Latent Space](https://mlsanity.com/paper/2106.07156/) (2021)
- [Domain Adversarial Reinforcement Learning](https://mlsanity.com/paper/2102.07097/) (2021)
- [Goal-Conditioned Predictive Coding for Offline Reinforcement Learning](https://mlsanity.com/paper/2307.03406/) (2023)
- [Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization](https://mlsanity.com/paper/2103.11144/) (2021)
- [Active Learning in Gaussian Process State Space Model](https://mlsanity.com/paper/2108.00819/) (2021)
- [Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning](https://mlsanity.com/paper/2203.12048/) (2022)
- [Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07397/) (2022)

## Abstract (arXiv)

Extending the capabilities of robotics to real-world complex, unstructured environments requires the need of developing better perception systems while maintaining low sample complexity. When dealing with high-dimensional state spaces, current methods are either model-free or model-based based on reconstruction objectives. The sample inefficiency of the former constitutes a major barrier for applying them to the real-world. The later, while they present low sample complexity, they learn latent spaces that need to reconstruct every single detail of the scene. In real environments, the task typically just represents a small fraction of the scene. Reconstruction objectives suffer in such scenarios as they capture all the unnecessary components. In this work, we present MIRO, an information theoretic representational learning algorithm for model-based reinforcement learning. We design a latent space that maximizes the mutual information with the future information while being able to capture all the information needed for planning. We show that our approach is more robust than reconstruction objectives in the presence of distractors and cluttered scenes