A Perspective on Objects and Systematic Generalization in Model-Based RL

Abstract

In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound features (objects) do not simply emerge in connectionist models of the world. We identify several requirements that need to be fulfilled in overcoming this limitation and highlight corresponding inductive biases.

Accepted to the ICML 2019 workshop on Workshop on Generative Modeling and Model-Based Reasoning for Robotics and AI

References in corpus (5)

• Recurrent Models of Visual Attention
• Interaction Networks for Learning about Objects, Relations and Physics
• A simple neural network module for relational reasoning
• Poincaré Embeddings for Learning Hierarchical Representations
• AI Safety Gridworlds