Can I read An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning on EtoBox?

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning by Yoon, Jaesik; Wu, Yi-Fu; Bae, Heechul; Ahn, Sungjin is a scholarly article available to read on EtoBox.

What is An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning about?

Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effective pre-training technique for various downstream tasks in terms of sample efficiency, systematic generalization, and reasoning. Although image-based reinforcement learning (RL) is one of the most important and thus frequently mentioned such downstream tasks, the benefit in RL has surprisingly not been investigated systematically thus far. Instead, most of the evaluations have focused on rather indirect metrics such as segmentation quality and object property prediction accuracy. In this paper, we investigate the effectiveness of OCR pre-training for image-based reinforcement learning via empirical experiments. For systematic evaluation, we introduce a simple object-centric visual RL benchmark and conduct experiments to answer questions such as ``Does OCR pre-training improve performance on object-centric tasks?'' and ``Can OCR pre-training help with out-of-distribution generalization?''. Our results provide empirical evidence for valuable insights into the effectiveness of OCR pre-training for RL and t

Author

Yoon, Jaesik; Wu, Yi-Fu; Bae, Heechul; Ahn, Sungjin

Published

2023

Language

EN