Internet Archive Scholar
Filters
























39 Hits in 4.5 sec

Balancing Exploration for Online Receding Horizon Learning Control with Provable Regret Guarantees [article]

Deepan Muthirayan, Jianjun Yuan, Pramod P. Khargonekar
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (387.8 kB)
https://web.archive.org/web/20220104020946/https://arxiv.org/pdf/2010.07269v13.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2010.07269v13 fatcat:hlf3z7jitrd4hnlzguqhiytpny

Other Versions

2021 pre-print
arXiv:2010.07269v12 fatcat:l367irh6qncqziaxt5l5k47fua
2021 pre-print
arXiv:2010.07269v11 fatcat:2eglv7353nhtbajbh7bxuibd6q
2021 pre-print
arXiv:2010.07269v10 fatcat:ylfydnosxbhwhjkrpsizoh2wye
2021 pre-print
arXiv:2010.07269v9 fatcat:uo5d4nu5tzc6vhukzdmuucz6cu
2021 pre-print
arXiv:2010.07269v8 fatcat:p55yse5645gplprlx4h6ddrzvm
2021 pre-print
arXiv:2010.07269v7 fatcat:3grgiz3jlndphcnwk6yi2dzf4i
2021 pre-print
arXiv:2010.07269v6 fatcat:pt5zcnmjwnef3eix5xtwb6mcfa
2020 pre-print
arXiv:2010.07269v5 fatcat:4hfep33hafhjddn62dgquj2r4q
2020 pre-print
arXiv:2010.07269v4 fatcat:knmmmtsokndarldoezhzb4zuqe
2020 pre-print
arXiv:2010.07269v3 fatcat:djrjvlipvzee3dm7iw35baaff4
2020 pre-print
arXiv:2010.07269v2 fatcat:taxxf2ly6vhgblabculpq4xuqq
2020 pre-print
arXiv:2010.07269v1 fatcat:3byi55ssf5g5rpfqelelafuwam
We address the problem of simultaneously learning and control in an online receding horizon control setting.  ...  We propose a novel approach to explore in an online receding horizon setting. The key challenge is to ensure that the control generated by the receding horizon controller is persistently exciting.  ...  Balancing Exploration for Online Receding Horizon Learning Control with Provable Regret Guarantees arXiv:2010.07269v13  ... 
arXiv:2010.07269v14 fatcat:4xi7n4y5dnbnjmqafnarx6o3xy
Multiple Versions
Citation

Deepan Muthirayan, Jianjun Yuan, Pramod P. Khargonekar. "Balancing Exploration for Online Receding Horizon Learning Control with Provable Regret Guarantees." arXiv (2021)

Online Learning for Predictive Control with Provable Regret Guarantees [article]

Deepan Muthirayan, Jianjun Yuan, Dileep Kalathil, Pramod P. Khargonekar
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (349.9 kB)
https://web.archive.org/web/20220423084944/https://arxiv.org/pdf/2111.15041v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2111.15041v1 fatcat:lprs244zqrbdfgxygkoqq6n5xu
Specifically, we study the online learning problem where the control algorithm does not know the true system model and has only access to a fixed-length (that does not grow with the control horizon) preview  ...  We study the problem of online learning in predictive control of an unknown linear dynamical system with time varying cost functions which are unknown apriori.  ...  In sharp contrast to these existing works, our goal is to develop an online learning MPC algorithm with provable finite time performance guarantees.  ... 
arXiv:2111.15041v2 fatcat:he43ygi3bjegzj2we7si2btdg4
Multiple Versions
Citation

Deepan Muthirayan, Jianjun Yuan, Dileep Kalathil, Pramod P. Khargonekar. "Online Learning for Predictive Control with Provable Regret Guarantees." arXiv (2022)

Meta-Learning Guarantees for Online Receding Horizon Learning Control [article]

Deepan Muthirayan, Pramod P. Khargonekar
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (369.1 kB)
https://web.archive.org/web/20220115010938/https://arxiv.org/pdf/2010.11327v14.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2010.11327v1 fatcat:pyfypovdkzhq3e44yyjwgqxbe4
2020 pre-print
arXiv:2010.11327v2 fatcat:mu2gdjbtdngzvmzx6pary42gdy
2020 pre-print
arXiv:2010.11327v3 fatcat:rhl24mjw2zcyfevehbpw5ftvxe
2020 pre-print
arXiv:2010.11327v4 fatcat:m7arqsixh5dzlcahxvfzmeclge
2020 pre-print
arXiv:2010.11327v5 fatcat:movc74n6gzbbxk7khyxatfxqoi
2021 pre-print
arXiv:2010.11327v6 fatcat:takee2u7hnecbiclcvnxg3ozmm
2021 pre-print
arXiv:2010.11327v7 fatcat:itus7nph25gehcmkjguypgpr74
2021 pre-print
arXiv:2010.11327v8 fatcat:avak6xzwynhdjnl6rlsi4fu53a
2021 pre-print
arXiv:2010.11327v9 fatcat:dxw24pyhxvhg3h7bqo4slg73vy
2021 pre-print
arXiv:2010.11327v10 fatcat:cg2tvti6wjfw5j5n7764e3xr5m
2021 pre-print
arXiv:2010.11327v11 fatcat:pzikfuyqordkzifoixp4pxqwti
2021 pre-print
arXiv:2010.11327v12 fatcat:ccof66am2rgjxktkazsxebfh24
2021 pre-print
arXiv:2010.11327v13 fatcat:asawpt2tmfgmlco4zceirmvbcm
In this paper we provide provable regret guarantees for an online meta-learning receding horizon control algorithm in an iterative control setting.  ...  By analysing conditions under which sub-linear regret is achievable, we prove that the meta-learning online receding horizon controller achieves an average of the dynamic regret for the controller cost  ...  For this setting we propose and study an online model-based meta-learning Receding Horizon Control (RHC) algorithm.  ... 
arXiv:2010.11327v14 fatcat:asbudhtn2bex7bqkbetkb4z3ki
Multiple Versions
Citation

Deepan Muthirayan, Pramod P. Khargonekar. "Meta-Learning Guarantees for Online Receding Horizon Learning Control." arXiv (2022)

Online Learning Robust Control of Nonlinear Dynamical Systems [article]

Deepan Muthirayan, Pramod P. Khargonekar
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (314.2 kB)
https://web.archive.org/web/20210616200148/https://arxiv.org/pdf/2106.04092v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

We propose an online controller and present guarantees for the metric R^p_t when the maximum possible attenuation is given by γ, which is a system constant.  ...  We also characterize the lower bound on the required prediction horizon for these guarantees to hold in terms of the system constants.  ...  We use a receding horizon control approach that minimizes the cost-to-go for a horizon M with the previewed disturbances and cost functions.  ... 
arXiv:2106.04092v1 fatcat:eswglw6apvbvvdf3zswoden7bq
Citation

Deepan Muthirayan, Pramod P. Khargonekar. "Online Learning Robust Control of Nonlinear Dynamical Systems." arXiv (2021)

Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis [article]

Yingying Li, Xin Chen, Na Li
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (507.2 kB)
https://web.archive.org/web/20200923191322/https://arxiv.org/pdf/1906.11378v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2019 pre-print
arXiv:1906.11378v1 fatcat:7fg7ex3cvrgwhcy4m2x6g2gn34
2019 pre-print
arXiv:1906.11378v2 fatcat:6yftdna65jcelpxj2zpur7rstm
We design online algorithms, Receding Horizon Gradient-based Control (RHGC), that utilize the predictions through finite steps of gradient computations.  ...  This paper studies the online optimal control problem with time-varying convex stage costs for a time-invariant linear dynamical system, where a finite lookahead window of accurate predictions of the stage  ...  In this paper, we propose novel gradient-based online control algorithms, receding horizon gradientbased control (RHGC), and provide nonasymptotic optimality guarantees by dynamic regrets.  ... 
arXiv:1906.11378v3 fatcat:3cjsuax45zcxzarr7n7neykfaa
Multiple Versions
Citation

Yingying Li, Xin Chen, Na Li. "Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis." arXiv (2019)

Value Directed Exploration in Multi-Armed Bandits with Structured Priors [article]

Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml
2017 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (581.4 kB)
https://web.archive.org/web/20191020133222/https://arxiv.org/pdf/1704.03926v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

Other Versions

2017 pre-print
arXiv:1704.03926v1 fatcat:e6kgoyjwojc2lexxf6t4to23fi
In this paper, we propose an algorithm for Bayesian multi-armed bandits that utilizes value-function-driven online planning techniques.  ...  The algorithm enjoys a sub-linear performance guarantee and we present simulation results that confirm its strength in problems with structured priors.  ...  This is an instance of receding horizon control, a common approach to solving online planning and reinforcement learning problems [Sutton and Barto, 2016] .  ... 
arXiv:1704.03926v2 fatcat:6ltuelyqyvdtjofwzx7vmtjeem
Multiple Versions
Citation

Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml. "Value Directed Exploration in Multi-Armed Bandits with Structured Priors." arXiv (2017)

Online Convex Optimization Using Predictions

Niangjun Chen, Anish Agarwal, Adam Wierman, Siddharth Barman, Lachlan L.H. Andrew
2015 Proceedings of the 2015 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems - SIGMETRICS '15  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (417.1 kB)
https://web.archive.org/web/20170922070010/http://authors.library.caltech.edu/58891/2/1504.06681v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

prediction error models it is possible to use Averaging Fixed Horizon Control (AFHC) to simultaneously achieve sublinear regret and constant competitive ratio in expectation using only a constant-sized  ...  We prove that achieving sublinear regret and constant competitive ratio for online algorithms requires the use of an unbounded prediction window in adversarial settings, but that under more realistic stochastic  ...  Given the focus of this paper on predictions, the most natural choice of an algorithm to consider is Receding Horizon Control (RHC), a.k.a., Model Predictive Control (MPC).  ... 
doi:10.1145/2745844.2745854 dblp:conf/sigmetrics/ChenAWBA15 fatcat:shjdpuchnncbfdvwz2vogzox5e
Citation

Niangjun Chen, Anish Agarwal, Adam Wierman, Siddharth Barman, Lachlan L.H. Andrew. "Online Convex Optimization Using Predictions." Proceedings of the 2015 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems - SIGMETRICS '15 (2015) 191-204

Online Convex Optimization Using Predictions

Niangjun Chen, Anish Agarwal, Adam Wierman, Siddharth Barman, Lachlan L.H. Andrew
2015 Performance Evaluation Review  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (417.1 kB)
https://web.archive.org/web/20170922070010/http://authors.library.caltech.edu/58891/2/1504.06681v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

prediction error models it is possible to use Averaging Fixed Horizon Control (AFHC) to simultaneously achieve sublinear regret and constant competitive ratio in expectation using only a constant-sized  ...  We prove that achieving sublinear regret and constant competitive ratio for online algorithms requires the use of an unbounded prediction window in adversarial settings, but that under more realistic stochastic  ...  Given the focus of this paper on predictions, the most natural choice of an algorithm to consider is Receding Horizon Control (RHC), a.k.a., Model Predictive Control (MPC).  ... 
doi:10.1145/2796314.2745854 fatcat:zd5fxkzcdvbcbfc66aa5twv534
Citation

Niangjun Chen, Anish Agarwal, Adam Wierman, Siddharth Barman, Lachlan L.H. Andrew. "Online Convex Optimization Using Predictions." Performance Evaluation Review 43.1 (2015) 191-204

Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning [article]

Sebastian Curi, Felix Berkenkamp, Andreas Krause
2020 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.8 MB)
https://web.archive.org/web/20201204234056/https://arxiv.org/pdf/2006.08684v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2006.08684v1 fatcat:xrghjbwe5fcnfokrjcudvrbfki
2020 pre-print
arXiv:2006.08684v2 fatcat:m7ktt5ulxfgmvb3w6hxicvliga
Furthermore, we analyze H-UCRL and construct a general regret bound for well-calibrated models, which is provably sublinear in the case of Gaussian Process models.  ...  Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods.  ...  Acknowledgments and Disclosure of Funding This project has received funding from the European Research Council (ERC) under the European Unions Horizon 2020 research and innovation program grant agreement  ... 
arXiv:2006.08684v3 fatcat:5uyz3uxicbf7fkmesv6rdkg6im
Multiple Versions
Citation

Sebastian Curi, Felix Berkenkamp, Andreas Krause. "Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning." arXiv (2020)

An Online-Learning Approach to Inverse Optimization [article]

Andreas Bärmann and Alexander Martin and Sebastian Pokutta and Oskar Schneider
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (987.7 kB)
https://web.archive.org/web/20200401000544/https://arxiv.org/pdf/1810.12997v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2018 pre-print
arXiv:1810.12997v1 fatcat:rxt6sy24qbcb5er4vtxqjiu7eq
Our approach is based on online learning and works for linear objectives over arbitrary feasible sets for which we have a linear optimization oracle.  ...  When applied to the stochastic offline case, our algorithms are able to give guarantees on the quality of the learned objectives in expectation.  ...  Acknowledgements This research was partially supported by NSF CAREER award CMMI-1452463 and by the Bavarian Ministry of Economic Affairs, Regional Development and Energy through the Center for Analytics  ... 
arXiv:1810.12997v2 fatcat:ksq3hk5eqzaz3pinf3ac4y7yea
Multiple Versions
Citation

Andreas Bärmann and Alexander Martin and Sebastian Pokutta and Oskar Schneider. "An Online-Learning Approach to Inverse Optimization." arXiv (2020)

FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis [article]

Aman Sinha, Matthew O'Kelly, Hongrui Zheng, Rahul Mangharam, John Duchi, Russ Tedrake
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (6.4 MB)
https://web.archive.org/web/20200912021215/https://arxiv.org/pdf/2003.03900v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2003.03900v1 fatcat:3gs4urmwbbgk7f4scejvcffkhi
Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. This work makes algorithmic contributions to both challenges.  ...  In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive strategies.  ...  [2] establish regret bounds for adaptive control methods applied to LTI systems, tightening the relationship to online learning.  ... 
arXiv:2003.03900v2 fatcat:xaxnxeensnhyliht7yrjti6amy
Multiple Versions
Citation

Aman Sinha, Matthew O'Kelly, Hongrui Zheng, Rahul Mangharam, John Duchi, Russ Tedrake. "FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis." arXiv (2020)

Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator [article]

Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (710.2 kB)
https://web.archive.org/web/20200829191755/https://arxiv.org/pdf/1801.05039v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2018 pre-print
arXiv:1801.05039v2 fatcat:5rjcpcpaqfhnhblgamrnxnlcci
2018 pre-print
arXiv:1801.05039v1 fatcat:oylvwhtl55gxncu63nilc3z5dq
Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the  ...  In contrast, system identification and model based planning in optimal control theory have a much more solid theoretical footing, where much is known with regards to their computational and statistical  ...  K. thanks Emo Todorov, Aravind Rajeswaran, Kendall Lowrey, Sanjeev Arora, and Elad Hazan for helpful discussions. S. K. and M. F. also thank Ben Recht for helpful discussions. R.  ... 
arXiv:1801.05039v3 fatcat:hf7gpybbxnfkrbuhzladrgvkby
Multiple Versions
Citation

Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi. "Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator." arXiv (2019)

Reinforcement Learning: A Survey

L. P. Kaelbling, M. L. Littman, A. W. Moore
1996 The Journal of Artificial Intelligence Research  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (523.4 kB)
https://web.archive.org/web/20190426102937/https://jair.org/index.php/jair/article/download/10166/24110

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.  ...  Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment.  ...  Acknowledgements Thanks to Marco Dorigo and three anonymous reviewers for comments that have helped to improve this paper.  ... 
doi:10.1613/jair.301 fatcat:nbo23vmu6rfz3ctpjbk7sdcnt4
DOAJ Szczepanski
Citation

L. P. Kaelbling, M. L. Littman, A. W. Moore. "Reinforcement Learning: A Survey." The Journal of Artificial Intelligence Research (1996) 237-285

Reinforcement Learning: A Survey [article]

L. P. Kaelbling, M. L. Littman, A. W. Moore
1996 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
File Archive PDF (506.5 kB)
https://archive.org/download/arxiv-cs9605103/cs9605103.pdf

The Internet Archive has a preservation copy of this work in our general collections. The file type is application/pdf.

It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.  ...  Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment.  ...  Acknowledgements Thanks to Marco Dorigo and three anonymous reviewers for comments that have helped to improve this paper.  ... 
arXiv:cs/9605103v1 fatcat:ze737h6wnfdhjf52hiz4gpogxq
Citation

L. P. Kaelbling, M. L. Littman, A. W. Moore. "Reinforcement Learning: A Survey." arXiv (1996)

Online Optimization with Predictions and Non-convex Losses [article]

Yiheng Lin, Gautam Goel, Adam Wierman
2020 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200905235330/https://arxiv.org/pdf/1911.03827v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2019 pre-print
arXiv:1911.03827v1 fatcat:6tun4en6c5bqlejwbdcwlir3pq
In this work, we give two general sufficient conditions that specify a relationship between the hitting and movement costs which guarantees that a new algorithm, Synchronized Fixed Horizon Control (SFHC  ...  Our results provide the first constant, dimension-free competitive ratio for online non-convex optimization with movement costs.  ...  CONCLUDING REMARKS In this paper we have studied the problem of online optimization with movement costs and, for the first time, provided algorithms with provable guarantees for the case when the hitting  ... 
arXiv:1911.03827v2 fatcat:m5dmpievhvfkfiqkuwwk3zoxoe
Multiple Versions
Citation

Yiheng Lin, Gautam Goel, Adam Wierman. "Online Optimization with Predictions and Non-convex Losses." arXiv (2020)

« Previous Showing results 1 — 15 out of 39 results