{"641567":{"#nid":"641567","#data":{"type":"event","title":"ML Ph.D. Thesis Proposal: Jiachen Yang","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E:\u0026nbsp;Cooperation in Multi-Agent Reinforcement Learning\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Thursday, December 3rd, 2020\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 1:00 pm - 2:30 pm Eastern time\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022https:\/\/bluejeans.com\/684552748\u0022 id=\u0022LPlnk711156\u0022\u003Ehttps:\/\/bluejeans.com\/684552748\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EStudent\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EJiachen Yang\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMachine Learning PhD Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003EComputational Science and Engineering\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cul\u003E\r\n\t\u003Cli\u003EDr. Hongyuan Zha (advisor)\u0026nbsp;- School of Computational Science and Engineering, Georgia Institute of Technology)\u003C\/li\u003E\r\n\t\u003Cli\u003EDr. Tuo Zhao -\u0026nbsp;School of Industrial and Systems Engineering,\u0026nbsp;Georgia Institute of Technology\u003C\/li\u003E\r\n\t\u003Cli\u003EDr. Charles Isbell -\u0026nbsp;School of Interactive Computing,\u0026nbsp;Georgia Institute of Technology\u003C\/li\u003E\r\n\u003C\/ul\u003E\r\n\r\n\u003Ch4\u003E\u0026nbsp;\u003C\/h4\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EAs progress in deep reinforcement learning (RL) gives rise to increasingly general and powerful artificial intelligence, there is a possible future in which multiple RL agents must learn and interact in a shared multi-agent environment. When a single principal has oversight of the multi-agent system, how should agents learn to cooperate via centralized training to achieve individual and global objectives? Alternatively, when agents belong to many self-interested principals with imperfectly-aligned objectives, how can cooperation emerge from fully-decentralized learning?\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn the first part of the thesis, we propose new algorithms for fully-cooperative multi-agent reinforcement learning (MARL) in the paradigm of centralized training with decentralized execution. Firstly, we propose a method based on multi-agent curriculum learning and multi-agent credit assignment to address the setting where global optimality is defined as the attainment of all individual goals. Secondly, we propose a hierarchical MARL algorithm to learn interpretable and useful skills for a multi-agent team to optimize a single shared reward.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn the second part, we propose learning algorithms to attain cooperation within a population of self-interested RL agents. We show that a new agent who is equipped with the new ability to incentivize other RL agents, and who explicitly accounts for the other agents\u0026#39; learning process, can overcome the challenging limitation of fully-decentralized training and generate emergent cooperation.\u0026nbsp;Building on successful techniques in the completed work, we propose in the remaining work to address two complex applications of MARL: 1) the problem of incentive design for\u0026nbsp;\u003Cem\u003Ein silico\u003C\/em\u003E\u0026nbsp;experimental economics, where one wishes to optimize a global objective only by intervening on the rewards of a population of independent RL agents; 2) the problem of adaptive mesh refinement in the finite element method for solving large-scale physical simulations of complex dynamics.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"ML@GT Ph.D. student Jiachen Yang will defend his thesis proposal."}],"uid":"34773","created_gmt":"2020-11-23 16:59:57","changed_gmt":"2020-11-23 17:01:49","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2020-12-03T13:00:00-05:00","event_time_end":"2020-12-03T14:30:00-05:00","event_time_end_last":"2020-12-03T14:30:00-05:00","gmt_time_start":"2020-12-03 18:00:00","gmt_time_end":"2020-12-03 19:30:00","gmt_time_end_last":"2020-12-03 19:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}