{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DF3NWQ3ELIORTIWXEKTPQWHEAF","short_pith_number":"pith:DF3NWQ3E","schema_version":"1.0","canonical_sha256":"1976db43645a1d19a2d722a6f858e40169e02b85da3f5aa1a1d5d6e4c9b64cdd","source":{"kind":"arxiv","id":"2105.14750","version":3},"attestation_state":"computed","paper":{"title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Jianhao Wang, Jin Zhang, Siyuan Li, Yang Yu","submitted_at":"2021-05-31T07:28:59Z","abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and subgoal representations. Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards. As the high-level policy selects subgoals in an online learned representation space, the dyn"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.14750","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-31T07:28:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2c3e54c99cf5f09df4a310e7ff19452296827c5aefbea3ac469773d3bb91072","abstract_canon_sha256":"74caad0447791c45efc2432e2bb4754db49dd00a23c61960afb71c03fc41634a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:16.673644Z","signature_b64":"+ytVRXvf6HabExLMvugLo30vHPCey8OMVduAPHghRbbfgf5XSwodIQ9j0L7La+ChbwHvqRBSuTtwvnD1Q1nKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1976db43645a1d19a2d722a6f858e40169e02b85da3f5aa1a1d5d6e4c9b64cdd","last_reissued_at":"2026-07-05T04:02:16.673192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:16.673192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Jianhao Wang, Jin Zhang, Siyuan Li, Yang Yu","submitted_at":"2021-05-31T07:28:59Z","abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and subgoal representations. Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards. As the high-level policy selects subgoals in an online learned representation space, the dyn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14750","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.14750/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.14750","created_at":"2026-07-05T04:02:16.673257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14750v3","created_at":"2026-07-05T04:02:16.673257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14750","created_at":"2026-07-05T04:02:16.673257+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF3NWQ3ELIOR","created_at":"2026-07-05T04:02:16.673257+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF3NWQ3ELIORTIWX","created_at":"2026-07-05T04:02:16.673257+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF3NWQ3E","created_at":"2026-07-05T04:02:16.673257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF","json":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF.json","graph_json":"https://pith.science/api/pith-number/DF3NWQ3ELIORTIWXEKTPQWHEAF/graph.json","events_json":"https://pith.science/api/pith-number/DF3NWQ3ELIORTIWXEKTPQWHEAF/events.json","paper":"https://pith.science/paper/DF3NWQ3E"},"agent_actions":{"view_html":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF","download_json":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF.json","view_paper":"https://pith.science/paper/DF3NWQ3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14750&json=true","fetch_graph":"https://pith.science/api/pith-number/DF3NWQ3ELIORTIWXEKTPQWHEAF/graph.json","fetch_events":"https://pith.science/api/pith-number/DF3NWQ3ELIORTIWXEKTPQWHEAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF/action/storage_attestation","attest_author":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF/action/author_attestation","sign_citation":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF/action/citation_signature","submit_replication":"https://pith.science/pith/DF3NWQ3ELIORTIWXEKTPQWHEAF/action/replication_record"}},"created_at":"2026-07-05T04:02:16.673257+00:00","updated_at":"2026-07-05T04:02:16.673257+00:00"}