{"id":1681,"date":"2026-10-06T19:04:17","date_gmt":"2026-10-06T19:04:17","guid":{"rendered":"https:\/\/www.cs.ubbcluj.ro\/~meco\/imitation-learning-via-deep-q-learning-for-multi-robot-path-planning-2026\/"},"modified":"2026-10-06T19:17:30","modified_gmt":"2026-10-06T19:17:30","slug":"imitation-learning-via-deep-q-learning-for-multi-robot-path-planning-2026","status":"publish","type":"post","link":"https:\/\/www.cs.ubbcluj.ro\/~meco\/imitation-learning-via-deep-q-learning-for-multi-robot-path-planning-2026\/","title":{"rendered":"Imitation Learning via Deep Q-Learning for Multi-robot Path Planning (2026)"},"content":{"rendered":"<div class=\"entry-content\">\n<p>Hybrid Artificial Intelligence Systems<\/p>\n<h2>Authors<\/h2>\n<p>Anik\u00f3 Kopacz, Enol Garc\u00eda Gonz\u00e1lez, Camelia Chira, Jos\u00e9 R. Villar<\/p>\n<h2>Abstract<\/h2>\n<p>Multi-robot path planning is essential for industrial operations, e.g., for manufacturing and warehouse logistics. Traditional path planning approaches may impose an unnecessary increase in computational demands when countered by unexpected events or failures. Thus, investigating machine learning approaches, such as reinforcement learning, is a compelling alternative that prioritizes robustness and continuously adapts to changes in the environment. First, we propose a hybrid centralized controller to solve the multi-robot path planning problem in grid-world environments. The hybrid policy combines an adaptive route planning algorithm with analytical conflict resolution to guide robots. Then, we propose a deep reinforcement learning approach, which applies imitation learning to utilize experiences from the hybrid policy to address multi-robot path planning. A decentralized Double Deep Q-network model is trained through independent learning to follow the expert policy. Computational experiments showed that the deep reinforcement learning approach is able to learn navigating in a grid-world environment.<\/p>\n<h2>Citation<\/h2>\n<pre class=\"wp-block-preformatted\">@Inproceedings{Kopacz2026ImitationLV,\n author = {Anik\u00f3 Kopacz and Enol Garc\u00eda Gonz\u00e1lez and Camelia Chira and Jos\u00e9 R. Villar},\n booktitle = {Hybrid Artificial Intelligence Systems},\n title = {Imitation Learning via Deep Q-Learning for Multi-robot Path Planning},\n year = {2026}\n}<\/pre>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Hybrid Artificial Intelligence Systems Authors Anik\u00f3 Kopacz, Enol Garc\u00eda Gonz\u00e1lez, Camelia Chira, Jos\u00e9 R. Villar Abstract Multi-robot path planning is essential for industrial operations, e.g., for manufacturing and warehouse logistics. Traditional path planning approaches may impose an unnecessary increase in computational demands when countered by unexpected events or failures. Thus, investigating machine learning approaches, such&hellip;<\/p>\n","protected":false},"author":6,"featured_media":1696,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[95,11],"_links":{"self":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1681"}],"collection":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/comments?post=1681"}],"version-history":[{"count":2,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1681\/revisions"}],"predecessor-version":[{"id":1700,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1681\/revisions\/1700"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/media\/1696"}],"wp:attachment":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/media?parent=1681"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/categories?post=1681"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/tags?post=1681"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}