From 778496ffc0439edca9309fcd027a9359bb8b1529 Mon Sep 17 00:00:00 2001 From: Daniele Gammelli Date: Wed, 14 Aug 2024 18:56:34 +0200 Subject: [PATCH] add bib entries --- _bibliography/ASL_Bib.bib | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/_bibliography/ASL_Bib.bib b/_bibliography/ASL_Bib.bib index 9876a01c..fd51e839 100755 --- a/_bibliography/ASL_Bib.bib +++ b/_bibliography/ASL_Bib.bib @@ -1776,6 +1776,18 @@ @inproceedings{SchneiderBylardEtAl2022 timestamp = {2021-11-04} } +@inproceedings{SchmidtGammelliEtAl2024, + author = {Schmidt, C. and Gammelli, D. and Harrison, J. and Pavone, M. and Rodrigues, F.}, + title = {Offline Hierarchical Reinforcement Learning via Inverse Optimization}, + booktitle = proc_NIPS, + keywords = {sub}, + note = {Submitted}, + abstract = {Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning hierarchical policies from static offline datasets presents a significant challenge. Crucially, actions taken by higher-level policies may not be directly observable within hierarchical controllers, and the offline dataset might have been generated using a different policy structure, hindering the use of standard offline learning algorithms. In this work, we propose OHIO: a framework for offline reinforcement learning (RL) of hierarchical policies. Our framework leverages knowledge of the policy structure to solve the \textit{inverse problem}, recovering the unobservable high-level actions that likely generated the observed data under our hierarchical policy. This approach constructs a dataset suitable for off-the-shelf offline training. We demonstrate our framework on robotic and network optimization problems and show that it substantially outperforms end-to-end RL methods and improves robustness. We investigate a variety of instantiations of our framework, both in direct deployment of policies trained offline and when online fine-tuning is performed.}, + year = {2024}, + owner = {gammelli}, + timestamp = {2024-08-14} +} + @incollection{SchmerlingPavone2019, author = {Schmerling, E. and Pavone, M.}, title = {Kinodynamic Planning}, @@ -4722,6 +4734,18 @@ @article{ChapmanBonalliEtAlTAC2021 url = {https://arxiv.org/abs/2101.12086} } +@article{CelestiniGammelliEtAl2024, + author = {Celestini, D. and Gammelli, D. and Guffanti, T. and D'Amico, S. and Capelli, E. and Pavone, M.}, + title = {Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling}, + journal = jrn_IEEE_RAL, + year = {2024}, + note = {Submitted}, + abstract = {Model predictive control (MPC) has established itself as the primary methodology for constrained control, enabling general-purpose robot autonomy in diverse real-world scenarios. However, for most problems of interest, MPC relies on the recursive solution of highly non-convex trajectory optimization problems, leading to high computational complexity and strong dependency on initialization. In this work, we present a unified framework to combine the main strengths of optimization-based and learning-based methods for MPC. Our approach entails embedding high-capacity, transformer-based neural network models within the optimization process for trajectory generation, whereby the transformer provides a near-optimal initial guess, or target plan, to a non-convex optimization problem. Our experiments, performed in simulation and the real world onboard a free flyer platform, demonstrate the capabilities of our framework to improve MPC convergence and runtime. Compared to purely optimization-based approaches, results show that our approach can improve trajectory generation performance by up to 75%, reduce the number of solver iterations by up to 45%, and improve overall MPC runtime by 7x without loss in performance.}, + keywords = {sub}, + owner = {gammelli}, + timestamp = {2024-08-14} +} + @inproceedings{CauligiCulbertsonEtAl2020, author = {Cauligi, A. and Culbertson, P. and Stellato, B. and Bertsimas, D. and Schwager, M. and Pavone, M.}, title = {Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control},