{"id":62325,"date":"2026-02-21T19:14:47","date_gmt":"2026-02-21T18:14:47","guid":{"rendered":"https:\/\/dcgi.fel.cvut.cz\/theses\/2024-holecto6\/"},"modified":"2026-02-21T19:14:50","modified_gmt":"2026-02-21T18:14:50","slug":"2024-holecto6","status":"publish","type":"thesis","link":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/","title":{"rendered":"Leveraging Reward Regularization in Imperfect Information Games"},"featured_media":0,"template":"","meta":{"_acf_changed":false},"class_list":["post-62325","thesis","type-thesis","status-publish","hentry"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.0.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<link rel=\"canonical\" href=\"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.0.1\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"PORTA\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"Leveraging Reward Regularization in Imperfect Information Games | DCGI\" \/>\n\t\t<meta property=\"og:description\" content=\"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2026-02-21T18:14:47+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2026-02-21T18:14:50+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary\" \/>\n\t\t<meta name=\"twitter:title\" content=\"Leveraging Reward Regularization in Imperfect Information Games | DCGI\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#listItem\",\"name\":\"Leveraging Reward Regularization in Imperfect Information Games\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#listItem\",\"position\":2,\"name\":\"Leveraging Reward Regularization in Imperfect Information Games\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#listItem\",\"name\":\"Home\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#organization\",\"name\":\"Katedra po\\u010d\\u00edta\\u010dov\\u00e9 grafiky a interakce, FEL, \\u010cVUT v Praze\",\"description\":\"DCGI web pages\",\"url\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/wp-content\\\/uploads\\\/cropped-logo-dcgi-web.png\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#organizationLogo\",\"width\":512,\"height\":512},\"image\":{\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#organizationLogo\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#webpage\",\"url\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/\",\"name\":\"Leveraging Reward Regularization in Imperfect Information Games | DCGI\",\"description\":\"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/theses\\\/2024\\\/holecto6\\\/#breadcrumblist\"},\"datePublished\":\"2026-02-21T19:14:47+01:00\",\"dateModified\":\"2026-02-21T19:14:50+01:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/\",\"name\":\"DCGI\",\"description\":\"DCGI web pages\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/dcgi.fel.cvut.cz\\\/en\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"Leveraging Reward Regularization in Imperfect Information Games | DCGI","description":"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is","canonical_url":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BreadcrumbList","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#listItem","position":1,"name":"Home","item":"https:\/\/dcgi.fel.cvut.cz\/en\/","nextItem":{"@type":"ListItem","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#listItem","name":"Leveraging Reward Regularization in Imperfect Information Games"}},{"@type":"ListItem","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#listItem","position":2,"name":"Leveraging Reward Regularization in Imperfect Information Games","previousItem":{"@type":"ListItem","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#listItem","name":"Home"}}]},{"@type":"Organization","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#organization","name":"Katedra po\u010d\u00edta\u010dov\u00e9 grafiky a interakce, FEL, \u010cVUT v Praze","description":"DCGI web pages","url":"https:\/\/dcgi.fel.cvut.cz\/en\/","logo":{"@type":"ImageObject","url":"https:\/\/dcgi.fel.cvut.cz\/wp-content\/uploads\/cropped-logo-dcgi-web.png","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#organizationLogo","width":512,"height":512},"image":{"@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#organizationLogo"}},{"@type":"WebPage","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#webpage","url":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/","name":"Leveraging Reward Regularization in Imperfect Information Games | DCGI","description":"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#website"},"breadcrumb":{"@id":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/#breadcrumblist"},"datePublished":"2026-02-21T19:14:47+01:00","dateModified":"2026-02-21T19:14:50+01:00"},{"@type":"WebSite","@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#website","url":"https:\/\/dcgi.fel.cvut.cz\/en\/","name":"DCGI","description":"DCGI web pages","inLanguage":"en-US","publisher":{"@id":"https:\/\/dcgi.fel.cvut.cz\/en\/#organization"}}]},"og:locale":"en_US","og:site_name":"PORTA","og:type":"article","og:title":"Leveraging Reward Regularization in Imperfect Information Games | DCGI","og:description":"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is","og:url":"https:\/\/dcgi.fel.cvut.cz\/en\/theses\/2024\/holecto6\/","article:published_time":"2026-02-21T18:14:47+00:00","article:modified_time":"2026-02-21T18:14:50+00:00","twitter:card":"summary","twitter:title":"Leveraging Reward Regularization in Imperfect Information Games | DCGI","twitter:description":"Reward regularization proved to be a powerful technique in reinforcement learning algorithms for solving imperfect information games. One such algorithm using this technique is the recently developed Regularized Nash Dynamics (RNaD), which achieved a human-expert level performance in the game Stratego. However, research about this technique has focused on two-player zero-sum games, and it is"},"aioseo_meta_data":{"post_id":"62325","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2025-10-12 09:05:33","updated":"2026-02-21 19:36:42","seo_analyzer_scan_date":null,"focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"_links":{"self":[{"href":"https:\/\/dcgi.fel.cvut.cz\/en\/wp-json\/wp\/v2\/thesis\/62325","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dcgi.fel.cvut.cz\/en\/wp-json\/wp\/v2\/thesis"}],"about":[{"href":"https:\/\/dcgi.fel.cvut.cz\/en\/wp-json\/wp\/v2\/types\/thesis"}],"version-history":[{"count":0,"href":"https:\/\/dcgi.fel.cvut.cz\/en\/wp-json\/wp\/v2\/thesis\/62325\/revisions"}],"wp:attachment":[{"href":"https:\/\/dcgi.fel.cvut.cz\/en\/wp-json\/wp\/v2\/media?parent=62325"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}