Zobrazeno 1 - 4
of 4
pro vyhledávání: '"da Silva, Bruno"'
We draw on the latest advancements in the physics community to propose a novel method for discovering the governing non-linear dynamics of physical systems in reinforcement learning (RL). We establish that this method is capable of discovering the un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1b1d130fb16a15b36ad176400bb69ac
http://arxiv.org/abs/2208.14501
http://arxiv.org/abs/2208.14501
When facing the problem of autonomously learning multiple tasks with reinforcement learning systems, researchers typically focus on solutions where just one parametrised policy per task is sufficient to solve them. However, in complex environments pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58e52d8a34938861dbe0b3f98f7e2fc5
Publikováno v:
The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making, Montreal, Quebec, Canada, 07-10/07/2019
info:cnr-pdr/source/autori:Vieri Giuliano Santucci, Emilio Cartoni, Bruno Castro da Silva, Gianluca Baldassarre/congresso_nome:The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making/congresso_luogo:Montreal, Quebec, Canada/congresso_data:07-10%2F07%2F2019/anno:2019/pagina_da:/pagina_a:/intervallo_pagine
info:cnr-pdr/source/autori:Vieri Giuliano Santucci, Emilio Cartoni, Bruno Castro da Silva, Gianluca Baldassarre/congresso_nome:The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making/congresso_luogo:Montreal, Quebec, Canada/congresso_data:07-10%2F07%2F2019/anno:2019/pagina_da:/pagina_a:/intervallo_pagine
Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning. Intrinsic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d06a2e370db48d4fadb47793bbde809c
https://arxiv.org/pdf/1905.02690.pdf
https://arxiv.org/pdf/1905.02690.pdf
In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but relate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5180dd8b30da6955a62431759ec76080