[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85159-en":3,"doc-seo-85159-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85159,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","TopoExplore Topological Discrimination for Archive-Based Exploration","Archive-based exploration such as Go-Explore and frontier methods drive agents to visited rarity or unknown boundaries, yet both ignore whether the behind-boundary unexplored region is actually enterable. TopoExplore adds a periodic topological pass to Go-Explore’s archive selection: enclosed unexplored voids in a visited-set occupancy grid are detected via flood fill, corresponding to H1 classes of a binary cubical complex, and only strict entrances receive a decaying selection bonus. Experiments on a controlled MiniGrid suite show faster entry steps and robustness to sealed decoys, plus analyzed failures and preliminary positives on other benchmarks.","arXiv :2607 .0997 1v 1 [ cs .AI] 10 Jul 2026  \nTopoExplore: Topological Discrimination for Archive-Based Exploration  \nPreliminary report  \nJason Carlson  \n[jcarlson212@gmail.com](jcarlson212@gmail.com)  \nJuly 2026 (v1—preliminary results; expanded evaluation to follow)  \nAbstract  \nArchive-based exploration methods such as Go-Explore select which visited state to return to using visitation rarity, and frontier methods in robotics return to the boundary of the unknown; neither asks whether the unexplored region behind a boundary is enterable at all. Exploration is not just about finding reward—it is about collecting a structurally complete experience for downstream learning and planning. We introduce TopoExplore, which augments Go-Explore cellselection with a periodic topological pass: enclosed unexplored regions (voids) of the visited-set occupancy grid are detected by flood fill—exactly the H1 classes of the binary cubical complex—and a decaying selection bonus is placed only on their strict entrances (gap or door cells), so sealed regions are never targeted and entered regions retire. On a controlled 18-environment MiniGrid suite (15 seeds, frozen hyperparameters) TopoExplore attains a 1.52 × geometric-mean speedup in median steps-to-first-entry over its exact Go-Explore ablation, versus 1.37 × for a strong frontier baseline on the same harness; critically, frontier exploration degrades precisely when sealed decoy structure appears (0.83–1.48 × on decoy environments vs. 1.65–2.11 × for TopoExplore), while TopoExplore holds its largest win on hard multi-interaction doors (10.9×) . We report an honest negative on Montezuma’s Revenge—without wall knowledge, unreachable occupancy artifacts capture the selection bonus and performance degrades as the bonus grows, isolating the wall-aware entrance test as the component that makes the method work—and a preliminary positive on HM3D scanned buildings, where the speedup over Go-Explore tracks scene difficulty (r =0.69) even as frontier selection dominates blanket coverage. The evidence supports a deliberately scoped claim: topology-aware selection pays off where enclosed structure must be discriminated, and remains competitive at open coverage—where frontier methods are strongest—despite not being tuned for that regime.  \n1 Introduction  \nHard-exploration methods answer the question “where should the agent go next?” with proxies: count-based and curiosity methods prefer rarely-visited or poorly-predicted states [2, 15 , 4]; GoExplore [10] archives visited cells and returns to under-visited ones; frontier exploration [19] drives to the boundary between known and unknown space. All of these treat the unexplored region as undifferentiated. Real environments are not undifferentiated: buildings contain rooms behind doorways, debris fields contain cavities, and—crucially—many enclosed regions are sealed: walled pockets, closed containers, reconstruction artifacts. An explorer that cannot tell an enterable enclosure from a sealed one wastes budget on boundaries that can never pay off, and dilutes its attention across large rims when only a single gap cell actually admits entry.  \nThis failure mode matters beyond benchmark exploration: navigation planners consume maps whose useful content is precisely paths, obstructions, and rooms, and an exploration mechanism that explicitly discovers which enclosed regions exist, which are enterable, and where their entrances are produces exactly that structure as a by-product of exploring.  \nTopoExplore makes this distinction explicit. It keeps the Go-Explore outer loop (select an archived cell, return to it, explore randomly, record new cells) and adds a periodic topological pass: enclosed unexplored regions of the visited-set occupancy grid are detected, and a selection bonus is placed on the cells from which an action actually enters them—their strict entrances—weighted by unexplored area and decayed by the number of inward actions already tried. This ","cbCaimKekSdwmlLR","https://ap.wps.com/l/cbCaimKekSdwmlLR","pdf",378170,1,9,"English","en",105,"# Abstract\n# Introduction\n## Contributions\n# Method\n## Setting and outer loop","[{\"question\":\"What problem does TopoExplore address compared with Go-Explore and frontier exploration?\",\"answer\":\"It targets the failure of treating all unexplored regions as undifferentiated by asking whether enclosed regions behind a boundary are enterable or sealed.\"},{\"question\":\"How does TopoExplore decide where the agent should explore next?\",\"answer\":\"It augments Go-Explore with a periodic topological pass that detects enclosed unexplored voids and awards a decaying bonus only to the strict entrance (gap or door) cells, with retirement after entry or exhausted entrances.\"},{\"question\":\"What do experiments show about TopoExplore versus baselines?\",\"answer\":\"On a controlled MiniGrid suite, TopoExplore yields a speedup in steps-to-first-entry and holds its advantage when sealed decoy structure appears, while frontier exploration degrades under sealed decoys; the report also includes a negative on Montezuma’s Revenge and a preliminary positive on HM3D.\"}]",1784201462,23,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"topoexplore-topological-discrimination-for-archive-based-exploration","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/topoexplore-topological-discrimination-for-archive-based-exploration/85159/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does TopoExplore address compared with Go-Explore and frontier exploration?","Question",{"text":74,"@type":75},"It targets the failure of treating all unexplored regions as undifferentiated by asking whether enclosed regions behind a boundary are enterable or sealed.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does TopoExplore decide where the agent should explore next?",{"text":79,"@type":75},"It augments Go-Explore with a periodic topological pass that detects enclosed unexplored voids and awards a decaying bonus only to the strict entrance (gap or door) cells, with retirement after entry or exhausted entrances.",{"name":81,"@type":72,"acceptedAnswer":82},"What do experiments show about TopoExplore versus baselines?",{"text":83,"@type":75},"On a controlled MiniGrid suite, TopoExplore yields a speedup in steps-to-first-entry and holds its advantage when sealed decoy structure appears, while frontier exploration degrades under sealed decoys; the report also includes a negative on Montezuma’s Revenge and a preliminary positive on HM3D.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]