paper-with-me

Papers

Physics-informed Imitative Reinforcement Learning for Real-world Driving

2024-06-18 · Hang Zhou, Yihao Qin, Dan Xu, Yiding Ji

Recent advances in imitative reinforcement learning (IRL) have considerably enhanced the ability of autonomous agents to assimilate expert demonstrations, leading to rapid skill acquisition in a range of demanding tasks. However, such learning-based agents face significant challenges when transferring knowledge to highly dynamic closed-loop environments. Their performance is significantly impacted by the conflicting optimization objectives of imitation learning (IL) and reinforcement learning (RL), sample inefficiency, and the complexity of uncovering the hidden world model and physics. To address this challenge, we propose a physics-informed IRL that is entirely data-driven. It leverages both expert demonstration data and exploratory data with a joint optimization objective, allowing the underlying physical principles of vehicle dynamics to emerge naturally from the training process. The performance is evaluated through empirical experiments and results exceed popular IL, RL and IRL algorithms in closed-loop settings on Waymax benchmark. Our approach exhibits 37.8% reduction in collision rate and 22.2% reduction in off-road rate compared to the baseline method.

📄 PDF Abstract BibTeX arXiv:2407.02508

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingImitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Imitative Membership Inference Attack

2025-09-08 · Yuntao Du, Yuetian Chen, Hanshen Xiao, Bruno Ribeiro 외 arxiv

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs r…

A Survey on Physics Informed Reinforcement Learning: Review and Open Problems

2023-09-05 · Chayan Banerjee, Kien Nguyen, Clinton Fookes, Maziar Raissi

The inclusion of physical information in machine learning frameworks has revolutionized many application areas. This involves enhancing the learning process by incorporating physical constraints and adhering to physical …

reinforcement-learningReinforcement Learning

Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models

2026-04-02 · Alex E. Ballentine, Nachiket U. Bapat, Raghvendra V. Cowlagi arxiv

The deployment of reinforcement learning (RL)-based controllers on physical systems is often limited by poor generalization to real-world scenarios, known as the simulation-to-reality (sim-to-real) gap. This gap is parti…

Synthetic Data GenerationReinforcement LearningOffline RL

PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation

2025-04-23 · Wenxuan Li, Hang Zhao, Zhiyuan Yu, Yu Du 외

While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving fricti…

FrictionModel-based Reinforcement LearningState Estimation

Physics-informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning

2025-04-07 · Zixin Jiang, Xuezheng Wang, Bing Dong

Physics-informed machine learning (PIML) provides a promising solution for building energy modeling and can serve as a virtual environment to enable reinforcement learning (RL) agents to interact and learn. However, chal…

Deep Reinforcement LearningPhysics-informed machine learningReinforcement Learning (RL)