Zobrazeno 1 - 10
of 354
pro vyhledávání: '"Shalabh Bhatnagar"'
Publikováno v:
Mathematics of Operations Research. 47:2138-2159
In this paper, we consider the stochastic iterative counterpart of the value iteration scheme wherein only noisy and possibly biased approximations of the Bellman operator are available. We call this counterpart the approximate value iteration (AVI)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17e73047748b4ead1e00b7ed6ce5b054
https://doi.org/10.1287/moor.2021.1202
https://doi.org/10.1287/moor.2021.1202
Publikováno v:
IEEE Transactions on Automatic Control. 67:4241-4247
Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive at the op
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8da96240508ffeedc4ef888677af7cd
https://doi.org/10.1109/tac.2021.3112851
https://doi.org/10.1109/tac.2021.3112851
Autor:
Prasenjit Karmakar, Shalabh Bhatnagar
Publikováno v:
IEEE Transactions on Automatic Control. 66:5941-5954
This paper compiles several aspects of the dynamics of stochastic approximation algorithms with Markov iterate-dependent noise when the iterates are not known to be stable beforehand. We achieve the same by extending the lock-in probability (i.e. the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6e973b8a044db43c5a3db68f884ef68
https://doi.org/10.1109/tac.2021.3057299
https://doi.org/10.1109/tac.2021.3057299
Publikováno v:
2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56657d038f0035cbd387077f6620298e
https://doi.org/10.1109/smc53654.2022.9945313
https://doi.org/10.1109/smc53654.2022.9945313
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 22:107-118
This paper presents our method for enabling a UAV quadrotor, equipped with a monocular camera, to autonomously avoid collisions with obstacles in unstructured and unknown indoor environments. When compared to obstacle avoidance in ground vehicular ro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::daba209a03f9a80b6b187e3158086a7c
https://doi.org/10.1109/tits.2019.2954952
https://doi.org/10.1109/tits.2019.2954952
Publikováno v:
Applied Intelligence. 51:1565-1579
Zeroth Order Bayesian Optimization (ZOBO) methods optimize an unknown function based on its black-box evaluations at the query locations. Unlike most optimization procedures, ZOBO methods fail to utilize gradient information even when it is available
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7cc90bd08dfbae7c96d8374a0db3401e
https://doi.org/10.1007/s10489-020-01896-w
https://doi.org/10.1007/s10489-020-01896-w
Publikováno v:
IEEE Control Systems Letters. 4:524-529
In this paper, we derive a generalization of the Speedy Q-learning (SQL) algorithm that was proposed in the Reinforcement Learning (RL) literature to handle slow convergence of Watkins' Q-learning. In most RL algorithms such as Q-learning, the Bellma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::530771884fb67920790853d968525205
https://doi.org/10.1109/lcsys.2020.2970555
https://doi.org/10.1109/lcsys.2020.2970555
Publikováno v:
Applied Intelligence. 50:3590-3606
Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control, robotic appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53b8c6e1b6d921941cd91c4b4a8e5deb
https://doi.org/10.1007/s10489-020-01758-5
https://doi.org/10.1007/s10489-020-01758-5
Publikováno v:
IEEE Control Systems Letters. 4:55-60
In a discounted reward Markov decision process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71f546c335ffb721d79178b350e6e552
https://doi.org/10.1109/lcsys.2019.2921158
https://doi.org/10.1109/lcsys.2019.2921158
Publikováno v:
Algorithms for Intelligent Systems ISBN: 9789811696497
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe0fdbe048e45588edeeab386747560e
https://doi.org/10.1007/978-981-16-9650-3_4
https://doi.org/10.1007/978-981-16-9650-3_4
