Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kaushik, Rituraj"'
The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. However, due to the inevitable r
Externí odkaz:
http://arxiv.org/abs/2201.13248
Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system with only a
Externí odkaz:
http://arxiv.org/abs/2003.04663
Publikováno v:
Frontiers in Robotics and AI. 6 (2020) 151
Repertoire-based learning is a data-efficient adaptation approach based on a two-step process in which (1) a large and diverse set of policies is learned in simulation, and (2) a planning or learning algorithm chooses the most appropriate policies ac
Externí odkaz:
http://arxiv.org/abs/1907.07029
Publikováno v:
Proceedings of the Conference on Robot Learning, PMLR 87:839-855, 2018
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the mode
Externí odkaz:
http://arxiv.org/abs/1806.09351
Autor:
Chatzilygeroudis, Konstantinos, Rama, Roberto, Kaushik, Rituraj, Goepp, Dorian, Vassiliades, Vassilis, Mouret, Jean-Baptiste
The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a policy that
Externí odkaz:
http://arxiv.org/abs/1703.07261
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Kaushik, Rituraj
Publikováno v:
Robotics [cs.RO]. Université de Lorraine, 2020. English
Artificial Intelligence [cs.AI]. Université de Lorraine, 2020. English. ⟨NNT : 2020LORR0105⟩
Artificial Intelligence [cs.AI]. Université de Lorraine, 2020. English. ⟨NNT : 2020LORR0105⟩
As soon as the robots step out in the real and uncertain world, they have to adapt to various unanticipated situations by acquiring new skills as quickly as possible. Unfortunately, on robots, current state-of-the-art reinforcement learning (e.g., de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2cab5154b15cdded40d5023cc8b1f336
https://hal.archives-ouvertes.fr/tel-02990155
https://hal.archives-ouvertes.fr/tel-02990155
Publikováno v:
Frontiers in Robotics and AI
Frontiers in Robotics and AI, Frontiers Media S.A., 2020, 6, ⟨10.3389/frobt.2019.00151⟩
Frontiers in Robotics and AI, Vol 6 (2020)
Frontiers in Robotics and AI, 2020, 6, ⟨10.3389/frobt.2019.00151⟩
Frontiers in Robotics and AI, Frontiers Media S.A., 2020, 6, ⟨10.3389/frobt.2019.00151⟩
Frontiers in Robotics and AI, Vol 6 (2020)
Frontiers in Robotics and AI, 2020, 6, ⟨10.3389/frobt.2019.00151⟩
Repertoire-based learning is a data-efficient adaptation approach based on a two-step process in which (1) a large and diverse set of policies is learned in simulation, and (2) a planning or learning algorithm chooses the most appropriate policies ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c52b718d43835fa7f58ecc242be7858
https://hal.inria.fr/hal-02462935/file/1907.07029.pdf
https://hal.inria.fr/hal-02462935/file/1907.07029.pdf
Autor:
Kaushik R; Inria, CNRS, Université de Lorraine, Nancy, France., Desreumaux P; Inria, CNRS, Université de Lorraine, Nancy, France., Mouret JB; Inria, CNRS, Université de Lorraine, Nancy, France.
Publikováno v:
Frontiers in robotics and AI [Front Robot AI] 2020 Jan 20; Vol. 6, pp. 151. Date of Electronic Publication: 2020 Jan 20 (Print Publication: 2019).
