paper-with-me

홈 › Papers

Probably Approximately Correct Vision-Based Planning using Motion Primitives

2020-02-28 · Sushant Veer, Anirudha Majumdar

This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i.e., environments unseen during training). We leverage the Probably Approximately Correct (PAC)-Bayes framework to obtain an upper bound on the expected cost of policies across all environments. Minimizing the PAC-Bayes upper bound thus trains policies that are accompanied by a certificate of performance on novel environments. The training pipeline we propose provides strong generalization guarantees for deep neural network policies by (a) obtaining a good prior distribution on the space of policies using Evolutionary Strategies (ES) followed by (b) formulating the PAC-Bayes optimization as an efficiently-solvable parametric convex optimization problem. We demonstrate the efficacy of our approach for producing strong generalization guarantees for learned vision-based motion planners through two simulated examples: (1) an Unmanned Aerial Vehicle (UAV) navigating obstacle fields with an onboard vision sensor, and (2) a dynamic quadrupedal robot traversing rough terrains with proprioceptive and exteroceptive sensors.

📄 PDF Abstract BibTeX arXiv:2002.12852

Code (1)

irom-lab/PAC-Vision-Planning 공식 구현 pytorch

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

On the Usability of Probably Approximately Correct Implication Bases

2017-01-04 · Daniel Borchmann, Tom Hanika, Sergei Obiedkov

We revisit the notion of probably approximately correct implication bases from the literature and present a first formulation in the language of formal concept analysis, with the goal to investigate whether such bases re…

The Probably Approximately Correct Learning Model in Computational Learning Theory

2025-11-11 · Rocco A. Servedio arxiv

This survey paper gives an overview of various known results on learning classes of Boolean functions in Valiant's Probably Approximately Correct (PAC) learning model and its commonly studied variants.

Probably Approximately Correct Labels

2025-06-12 · Emmanuel J. Candès, Andrew Ilyas, Tijana Zrnic

Obtaining high-quality labeled datasets is often costly, requiring either extensive human annotation or expensive experiments. We propose a method that supplements such "expert" labels with AI predictions from pre-traine…

Protein Foldingtext annotation

Regular Patterns - Probably Approximately Correct Language Model

2013-11-01 · WS 2013 11 · Octavian Popescu
Language ModelingLanguage ModellingmodelNatural Language Inference+1

Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis

2020-09-18 · Daniel Neider, Bishwamittra Ghosh

We propose a novel approach to understanding the decision making of complex machine learning models (e.g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference …

BIG-bench Machine LearningDecision Making