Discovering Object-Centric Generalized Value Functions From Pixels

Autor:	Nath, Somjit, Subbaraj, Gopeshh Raaj, Khetarpal, Khimya, Kahou, Samira Ebrahimi
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an object-centric manner geared towards control and fast adaptation remains an open research problem. In this paper, we introduce a method that tries to discover meaningful features from objects, translating them to temporally coherent "question" functions and leveraging the subsequent learned general value functions for control. We compare our approach with state-of-the-art techniques alongside other ablations and show competitive performance in both stationary and non-stationary settings. Finally, we also investigate the discovered general value functions and through qualitative analysis show that the learned representations are not only interpretable but also, centered around objects that are invariant to changes across tasks facilitating fast adaptation. Comment: Accepted at ICML 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.13892 Zobrazit plný text záznamu View this record from Arxiv