{"id":1972,"date":"2025-10-16T08:30:08","date_gmt":"2025-10-16T07:30:08","guid":{"rendered":"https:\/\/babel.isa.uma.es\/kipr\/?p=1972"},"modified":"2025-10-16T08:30:08","modified_gmt":"2025-10-16T07:30:08","slug":"inclusion-of-llms-in-multiple-task-learning-for-generating-rewards","status":"publish","type":"post","link":"https:\/\/babel.isa.uma.es\/kipr\/?p=1972","title":{"rendered":"Inclusion of LLMs in multiple task learning for generating rewards"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">Z. Lin, Y. Chen and Z. Liu,  <strong>AutoSkill: Hierarchical Open-Ended Skill Acquisition for Long-Horizon Manipulation Tasks via Language-Modulated Rewards,<\/strong> IEEE Transactions on Cognitive and Developmental Systems, vol. 17, no. 5, pp. 1141-1152, Oct. 2025, <a href=\"https:\/\/doi.org\/10.1109\/TCDS.2025.3551298\">10.1109\/TCDS.2025.3551298<\/a>.<\/h4>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>A desirable property of generalist robots is the ability to both bootstrap diverse skills and solve new long-horizon tasks in open-ended environments without human intervention. Recent advancements have shown that large language models (LLMs) encapsulate vast-scale semantic knowledge about the world to enable long-horizon robot planning. However, they are typically restricted to reasoning high-level instructions and lack world grounding, which makes it difficult for them to coordinately bootstrap and acquire new skills in unstructured environments. To this end, we propose AutoSkill, a hierarchical system that empowers the physical robot to automatically learn to cope with new long-horizon tasks by growing an open-ended skill library without hand-crafted rewards. AutoSkill consists of two key components: 1) an in-context skill chain generation and new skill bootstrapping guided by LLMs that inform the robot of discrete and interpretable skill instructions for skill retrieval and augmentation within the skill library; and 2) a zero-shot language-modulated reward scheme in conjunction with a meta prompter facilitates online new skill acquisition via expert-free supervision aligned with proposed skill directives. Extensive experiments conducted in both simulated and realistic environments demonstrate AutoSkill&#8217;s superiority over other LLM-based planners as well as hierarchical methods in expediting online learning for novel manipulation tasks.\n<\/p>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Z. Lin, Y. Chen and Z. Liu, AutoSkill: Hierarchical Open-Ended Skill Acquisition for Long-Horizon Manipulation Tasks via Language-Modulated Rewards, IEEE <span class=\"ellipsis\">&hellip;<\/span> <span class=\"more-link-wrap\"><a href=\"https:\/\/babel.isa.uma.es\/kipr\/?p=1972\" 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":[84],"tags":[562,518,581],"class_list":["post-1972","post","type-post","status-publish","format-standard","hentry","category-reinforcement-learning-in-ai","tag-llms","tag-multi-task-rl","tag-reward-generation"],"_links":{"self":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1972"}],"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=1972"}],"version-history":[{"count":1,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1972\/revisions"}],"predecessor-version":[{"id":1973,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/1972\/revisions\/1973"}],"wp:attachment":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1972"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1972"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1972"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}