Privileged Information Dropout in Reinforcement Learning

  • Kamienny, Pierre-Alexandre; Behbahani, Feryal; Arulkumaran, Kai*; Boehmer, Wendelin; Whiteson, Shimon
  • Accepted abstract
  • [PDF] [Slides] [Join poster session]
    Poster session from 15:00 to 16:00 EAT and from 20:45 to 21:45 EAT
    Obtain the zoom password from ICLR

Abstract

Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary tasks, and less commonly in the form of augmenting the inputs of agents. In this work, we investigate Privileged Information Dropout (PI-Dropout) for achieving the latter which can be applied equally to value-based and policy-based RL algorithms. Within a simple partially-observed environment, we demonstrate that PI-Dropout outperforms alternatives for leveraging privileged information, including distillation and auxiliary tasks, and can successfully utilise different types of privileged information. Finally, we analyse its effect on the learned representations.

If videos are not appearing, disable ad-block!