# Privileged Information Dropout in Reinforcement Learning

arXiv: https://arxiv.org/abs/2005.09220 · HTML: https://mlsanity.com/paper/2005.09220/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 8 of 8)

- [Privileged Sensing Scaffolds Reinforcement Learning](https://mlsanity.com/paper/2405.14853/) (2024)
- [Learning in POMDPs is Sample-Efficient with Hindsight Observability](https://mlsanity.com/paper/2301.13857/) (2023)
- [A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo](https://mlsanity.com/paper/2406.12563/) (2024)
- [MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning](https://mlsanity.com/paper/2109.10552/) (2021)
- [Unifying Agent Interaction and World Information for Multi-agent Coordination](https://mlsanity.com/paper/2509.25550/) (2025)
- [Driving Beyond Privilege: Distilling Dense-Reward Knowledge into Sparse-Reward Policies](https://mlsanity.com/paper/2512.04279/) (2025)
- [Offline RL With Resource Constrained Online Deployment](https://mlsanity.com/paper/2110.03165/) (2021)
- [Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck](https://mlsanity.com/paper/2109.08677/) (2021)

## Abstract (arXiv)

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 (pid) 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 pid 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.