Privileged Information Dropout in Reinforcement Learning

2020-05-19 · Pierre-Alexandre Kamienny, Kai Arulkumaran, Feryal Behbahani, Wendelin Boehmer, Shimon Whiteson

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.

📄 PDF Abstract BibTeX arXiv:2005.09220

Code (0)

등록된 구현이 없습니다.

Tasks

Formreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Deep Learning under Privileged Information Using Heteroscedastic Dropout

2018-05-29 · CVPR 2018 6 · John Lambert, Ozan Sener, Silvio Savarese

Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive comments, comparisons, and explanations to …

Deep Learning image-classification Image Classification Machine Translation+1

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

2025-08-04 · Dongchi Huang, Jiaqi Wang, Yang Li, Chunhe Xia 외 arxiv

Partial observability presents a significant challenge for Safe Reinforcement Learning (Safe RL), as it impedes the identification of potential risks and rewards. Leveraging specific types of privileged information durin…

Reinforcement Learning

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

2025-05-22 · Zhenjie Yang, Xiaosong Jia, QiFeng Li, Xue Yang 외

Reinforcement Learning (RL) can mitigate the causal confusion and distribution shift inherent to imitation learning (IL). However, applying RL to end-to-end autonomous driving (E2E-AD) remains an open problem for its tra…

Autonomous Driving Bench2Drive CARLA Leaderboard 2.0 Imitation Learning+4

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information

2024-12-09 · Junqiao Wang, Zhongliang Yu, Dong Zhou, Jiaqi Shi 외

The capability of UAVs for efficient autonomous navigation and obstacle avoidance in complex and unknown environments is critical for applications in agricultural irrigation, disaster relief and logistics. In this paper,…

Autonomous Navigation Benchmarking Deep Reinforcement Learning reinforcement-learning+1

Quadrotor Navigation using Reinforcement Learning with Privileged Information

2025-09-09 · Jonathan Lee, Abhishek Rathod, Kshitij Goel, John Stecklein 외 arxiv

This paper presents a reinforcement learning-based quadrotor navigation method that leverages efficient differentiable simulation, novel loss functions, and privileged information to navigate around large obstacles. Prio…