{"477331":{"#nid":"477331","#data":{"type":"event","title":"Cognitive Systems Seminar Series: Dr. H\u00e9ctor Mu\u00f1oz-Avila","body":[{"value":"\u003Cstrong\u003ERaising Expectations: Self-Monitoring Goal-Driven Autonomy Agents\u003C\/strong\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAbstract: I present our ongoing work on Goal-driven autonomy (GDA), a reflective model of goal reasoning that controls the focus of an agent\u2019s planning activities by dynamically resolving unexpected discrepancies between the outcome of the agent\u2019s actions and the agent\u2019s own expectations. Discrepancies frequently arise when solving tasks in complex environments. GDA agents have performed well on such tasks by integrating methods for discrepancy recognition, explanation, goal formulation, and goal management. However, they require substantial domain knowledge, including, planning knowledge, knowledge about what constitutes a discrepancy and how to resolve it. We present work for acquiring this knowledge that integrates case-based reasoning, reinforcement learning and hierarchical task network learning methods. We assess its utility on tasks from a real-time strategy game. Taking advantage of hierarchical planning principles, we also present recent work eliciting expectations that not only validate the next action but the overall plan trajectory without requiring validation against the complete state.\u003C\/p\u003E\u003Cp\u003EDr. H\u00e9ctor Mu\u00f1oz-Avila is currently serving as a program director at the National Science Foundation\u0027s (NSF) Robust Intelligence program. He is an associate professor at the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.cse.lehigh.edu\/\u0022 target=\u0022_blank\u0022\u003EDepartment of Computer\u0026nbsp;Science and Engineering\u003C\/a\u003E\u0026nbsp;at\u0026nbsp;\u003Ca href=\u0022http:\/\/www.lehigh.edu\/\u0022 target=\u0022_blank\u0022\u003ELehigh University\u003C\/a\u003E.\u003C\/p\u003E\u0026nbsp;\u003Cp\u003EDr. Mu\u00f1oz-Avila\u0027s is interested in intelligent systems that can assist people solving complex problems. This includes research on systems capable of acquiring and adapting episodic knowledge (i.e., case-based reasoning), generalizing and abstracting this episodic knowledge into general domain knowledge (i.e., machine learning), using this knowledge to solve new problems (i.e., planning), adapting to changes in the environment (i.e., agents) and introspectively reasoning about its own actions (i.e., cognitive systems). He is also interested in\u0026nbsp;\u003Ca href=\u0022http:\/\/www.cse.lehigh.edu\/%7Emunoz\/projects\/AIGames\/\u0022 target=\u0022_blank\u0022\u003Eadvancing game AI\u003C\/a\u003E\u0026nbsp;with AI techniques.\u003C\/p\u003E\u003Cp\u003EDr. Mu\u00f1oz-Avila is recipient of a\u0026nbsp;\u003Ca href=\u0022http:\/\/www3.lehigh.edu\/News\/V2news_story.asp?iNewsID=1989\u0026amp;strBack=%2Fdefault.asp\u0022 target=\u0022_blank\u0022\u003ENational Science Foundation (NSF) CAREER award\u003C\/a\u003E, two papers awards and held a Lehigh Class of 1961 Professorship. He has been chair for various international scientific meetings including the Sixth International Conference on Case-Based Reasoning (ICCBR-05) and the twenty-fifth Innovative Applications of AI Conference (IAAI-13). Dr. Mu\u00f1oz-Avila is currently a program director for Robust Intelligence at the National Science Fundation (NSF). He has been funded in the past by the Defense Advanced Research Projects Agency (DARPA), the Office of Naval Research (ONR), and the Naval Research Laboratory (NRL) and the Air Force Research Laboratory (AFRL).\u003C\/p\u003E\u003Cp\u003EHe holds a PhD (Dr. rer. nat.) in computer science from the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.uni-kl.de\/startseite\/\u0022 target=\u0022_blank\u0022\u003EUniversit\u00e4t Kaiserslautern\u003C\/a\u003E\u0026nbsp;(Germany), an MS in computer science, a BS in Mathematics and a BS in computer Science from the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.uniandes.edu.co\/\u0022 target=\u0022_blank\u0022\u003EUniversidad de los Andes\u003C\/a\u003E\u0026nbsp;(Colombia). \u003Cbr \/\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"In this talk, NSF\u0027s H\u00e9ctor Mu\u00f1oz-Avila presents his ongoing work on Goal-driven autonomy (GDA)."}],"uid":"27980","created_gmt":"2015-12-09 08:53:15","changed_gmt":"2017-04-13 21:17:28","author":"Alyson Key","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2016-01-15T15:00:00-05:00","event_time_end":"2016-01-15T16:00:00-05:00","event_time_end_last":"2016-01-15T16:00:00-05:00","gmt_time_start":"2016-01-15 20:00:00","gmt_time_end":"2016-01-15 21:00:00","gmt_time_end_last":"2016-01-15 21:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"hg_media":{"477971":{"id":"477971","type":"image","title":"H\u00e9ctor Mu\u00f1oz-Avila","body":null,"created":"1450285200","gmt_created":"2015-12-16 17:00:00","changed":"1475895230","gmt_changed":"2016-10-08 02:53:50","alt":"H\u00e9ctor Mu\u00f1oz-Avila","file":{"fid":"204116","name":"munoz-avila.jpg","image_path":"\/sites\/default\/files\/images\/munoz-avila_0.jpg","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/munoz-avila_0.jpg","mime":"image\/jpeg","size":29952,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/munoz-avila_0.jpg?itok=VptsV6t1"}}},"media_ids":["477971"],"groups":[{"id":"69599","name":"IPaT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78751","name":"Undergraduate students"},{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}