{"id":1896,"date":"2025-04-03T06:38:49","date_gmt":"2025-04-03T05:38:49","guid":{"rendered":"https:\/\/babel.isa.uma.es\/kipr\/?p=1896"},"modified":"2025-04-03T06:38:49","modified_gmt":"2025-04-03T05:38:49","slug":"on-the-explainability-of-deep-rl-and-its-improvement-through-the-integration-of-human-preferences","status":"publish","type":"post","link":"https:\/\/babel.isa.uma.es\/kipr\/?p=1896","title":{"rendered":"On the explainability of Deep RL and its improvement through the integration of human preferences"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">Georgios Angelopoulos, Luigi Mangiacapra, Alessandra Rossi, Claudia Di Napoli, Silvia Rossi, <strong>What is behind the curtain? Increasing transparency in reinforcement learning with human preferences and explanations,<\/strong> Engineering Applications of Artificial Intelligence, Volume 149, 2025, <a href=\"https:\/\/doi.org\/10.1016\/j.engappai.2025.110520\">10.1016\/j.engappai.2025.110520<\/a>.<\/h4>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>In this work, we investigate whether the transparency of a robot\u2019s behaviour is improved when human preferences on the actions the robot performs are taken into account during the learning process. For this purpose, a shielding mechanism called Preference Shielding is proposed and included in a reinforcement learning algorithm to account for human preferences. We also use the shielding to decide when to provide explanations of the robot\u2019s actions. We carried out a within-subjects study involving 26 participants to evaluate the robot\u2019s transparency. Results indicate that considering human preferences during learning improves legibility compared with providing only explanations. In addition, combining human preferences and explanations further amplifies transparency. Results also confirm that increased transparency leads to an increase in people\u2019s perception of the robot\u2019s safety, comfort, and reliability. These findings show the importance of transparency during learning and suggest a paradigm for robotic applications when a robot has to learn a task in the presence of or in collaboration with a human.\n<\/p>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Georgios Angelopoulos, Luigi Mangiacapra, Alessandra Rossi, Claudia Di Napoli, Silvia Rossi, What is behind the curtain? Increasing transparency in reinforcement <span class=\"ellipsis\">&hellip;<\/span> <span class=\"more-link-wrap\"><a href=\"https:\/\/babel.isa.uma.es\/kipr\/?p=1896\" class=\"more-link\"><span>Read More &rarr;<\/span><\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14],"tags":[309,445,175],"class_list":["post-1896","post","type-post","status-publish","format-standard","hentry","category-applications-of-reinforcement-learning-to-robots","tag-deep-reinforcement-learning","tag-explainability","tag-human-robot-integration"],"_links":{"self":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1896"}],"collection":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1896"}],"version-history":[{"count":1,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1896\/revisions"}],"predecessor-version":[{"id":1897,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1896\/revisions\/1897"}],"wp:attachment":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1896"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1896"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1896"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}