DeepAI AI Chat
Log In Sign Up

Mutual Information Maximization for Robust Plannable Representations

by   Yiming Ding, et al.
berkeley college

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


Learning Latent State Spaces for Planning through Reward Prediction

Model-based reinforcement learning methods typically learn models for hi...

High-Accuracy Model-Based Reinforcement Learning, a Survey

Deep reinforcement learning has shown remarkable success in the past few...

Temporal Predictive Coding For Model-Based Planning In Latent Space

High-dimensional observations are a major challenge in the application o...

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

While reinforcement learning (RL) methods that learn an internal model o...

Efficient Reconstruction of Stochastic Pedigrees

We introduce a new algorithm called Rec-Gen for reconstructing the gene...

Learning Efficient Representation for Intrinsic Motivation

Mutual Information between agent Actions and environment States (MIAS) q...

Volumetric Objectives for Multi-Robot Exploration of Three-Dimensional Environments

Volumetric objectives for exploration and perception tasks seek to captu...