Mutual Information Maximization for Robust Plannable Representations

Yiming Ding, Ignasi Clavera, Pieter Abbeel

Keywords: reinforcement learning, robust learning, model based, planning, representation learning

TL;DR: Representational learning objective for planning that is robust to visual distractors

Abstract:

Extending the capabilities of robotics to real-world complex, unstructured environments requires the capability 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 with reconstruction based objectives. The sample inefficiency of the former constitutes a major barrier for applying them to the real-world. While the latter present low sample complexity, they learn latent spaces that need to reconstruct every single detail of the scene. Real-world environments are unstructured and cluttered with objects. Capturing all the variability on the latent representation harms its applicability to downstream tasks. In this work, we present mutual information maximization for robust plannable representations (MIRO), an information theoretic representational learning objective for model-based reinforcement learning. Our objective optimizes for a latent space that maximizes the mutual information with future observations and emphasizes the relevant aspects of the dynamics, which allows to capture all the information needed for planning.
We show that our approach learns a latent representation that in cluttered scenes focuses on the task relevant features, ignoring the irrelevant aspects. At the same time, state-of-the-art methods with reconstruction objectives are unable to learn in such environments.