{"id":184776,"date":"2024-03-09T08:42:17","date_gmt":"2024-03-09T14:42:17","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2024\/03\/selfi-autonomous-self-improvement-with-reinforcement-learning-for-social-navigation"},"modified":"2024-03-09T08:42:17","modified_gmt":"2024-03-09T14:42:17","slug":"selfi-autonomous-self-improvement-with-reinforcement-learning-for-social-navigation","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2024\/03\/selfi-autonomous-self-improvement-with-reinforcement-learning-for-social-navigation","title":{"rendered":"SELFI: Autonomous Self-improvement with Reinforcement Learning for Social Navigation"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/ElTAc_9a2l4?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>On socially compliant navigation: Researchers show how real-world RL-based finetuning can enable mobile robots to adapt on the fly to the behavior of humans, to obstacles, and other challenges associated with real-world navigation:<\/p>\n<hr>\n<p>Abstract.<\/p>\n<p>We propose an online reinforcement learning approach, SELFI, to fine-tune a control policy trained on model-based learning. In SELFI, we combine the best parts of data efficient model-based learning with flexible model-free reinforcement learning, alleviating both of their limitations. We formulate a combined objective: the objective of the model-based learning and the learned Q-value from model-free reinforcement learning. By maximizing this combined objective in the online learning process, we improve the performance of the pre-trained policy in a stable manner. Main takeaways from our method are.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>On socially compliant navigation: Researchers show how real-world RL-based finetuning can enable mobile robots to adapt on the fly to the behavior of humans, to obstacles, and other challenges associated with real-world navigation: Abstract. We propose an online reinforcement learning approach, SELFI, to fine-tune a control policy trained on model-based learning. In SELFI, we combine [\u2026]<\/p>\n","protected":false},"author":709,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[31,6],"tags":[],"class_list":["post-184776","post","type-post","status-publish","format-standard","hentry","category-policy","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/184776","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/709"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=184776"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/184776\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=184776"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=184776"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=184776"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}