paper-with-me

Papers

PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC

2026-04-09 · Mohsen Amiri, Mohsen Amiri, Ali Beikmohammadi, Sindri Magnuśson, Mehdi Hosseinzadeh arxiv

This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feasible planner agent available exclusively during training. We formalize this as a Partially Observable Markov Decision Process (POMDP) in which a planner agent with access to an approximate dynamical model and privileged state information guides a learning agent that observes only a lossy projection of the true state. To realize this framework, we introduce an anytime-feasible Model Predictive Control (MPC) algorithm that serves as the planner agent. For the learning agent, we propose Planner-to-Policy Soft Actor-Critic (P2P-SAC), a method that distills the planner agent's privileged knowledge to mitigate partial observability and thereby improve both sample efficiency and final policy performance. We support this framework with rigorous theoretical analysis. Finally, we validate our approach in simulation using NVIDIA Isaac Lab and successfully deploy it on a real-world Unitree Go2 quadruped navigating complex, obstacle-rich environments.

📄 PDF Abstract BibTeX arXiv:2604.08036

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

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

Privileged Information Dropout in Reinforcement Learning

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

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 distilla…

Formreinforcement-learningReinforcement LearningReinforcement Learning (RL)

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 DrivingBench2DriveCARLA Leaderboard 2.0Imitation Learning+4

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

2025-10-03 · Yuda Song, Dhruv Rohatgi, Aarti Singh, J. Andrew Bagnell arxiv

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leve…

Reinforcement Learning

Provable Partially Observable Reinforcement Learning with Privileged Information

2024-12-01 · Yang Cai, Xiangyu Liu, Argyris Oikonomou, Kaiqing Zhang

Partial observability of the underlying states generally presents significant challenges for reinforcement learning (RL). In practice, certain \emph{privileged information}, e.g., the access to states from simulators, ha…

Partially Observable Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)