{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2UHQO5GZC2AL4Z2VDVPN3QHREH","short_pith_number":"pith:2UHQO5GZ","schema_version":"1.0","canonical_sha256":"d50f0774d91680be67551d5eddc0f121f04d0c1e8fd24988770618fa0dbc9031","source":{"kind":"arxiv","id":"2508.17751","version":1},"attestation_state":"computed","paper":{"title":"Multi-layer Abstraction for Nested Generation of Options (MANGO) in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Sinigaglia, Alessio Arcudi, Davide Sartor, Gian Antonio Susto, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2025-08-25T07:44:35Z","abstract_excerpt":"This paper introduces MANGO (Multilayer Abstraction for Nested Generation of Options), a novel hierarchical reinforcement learning framework designed to address the challenges of long-term sparse reward environments. MANGO decomposes complex tasks into multiple layers of abstraction, where each layer defines an abstract state space and employs options to modularize trajectories into macro-actions. These options are nested across layers, allowing for efficient reuse of learned movements and improved sample efficiency. The framework introduces intra-layer policies that guide the agent's transiti"},"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":"2508.17751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T07:44:35Z","cross_cats_sorted":[],"title_canon_sha256":"ff882bb295982c43b9dbb110e9058d3165aee7a17f90a5e38408d290265b7579","abstract_canon_sha256":"364f1fd76eb1a09a7f4867dc76b4a4a198a8752836246b3ec57d3b96533d4296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:47.068853Z","signature_b64":"4tpChD4DXsHimmoIM2sYMQiqaxkVk5lX82poRETOXLdI5kd/CrAyDit+YH0PfjhE6jGj2kInc/WtTh9Y7jYuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d50f0774d91680be67551d5eddc0f121f04d0c1e8fd24988770618fa0dbc9031","last_reissued_at":"2026-07-05T11:58:47.068302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:47.068302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-layer Abstraction for Nested Generation of Options (MANGO) in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Sinigaglia, Alessio Arcudi, Davide Sartor, Gian Antonio Susto, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2025-08-25T07:44:35Z","abstract_excerpt":"This paper introduces MANGO (Multilayer Abstraction for Nested Generation of Options), a novel hierarchical reinforcement learning framework designed to address the challenges of long-term sparse reward environments. MANGO decomposes complex tasks into multiple layers of abstraction, where each layer defines an abstract state space and employs options to modularize trajectories into macro-actions. These options are nested across layers, allowing for efficient reuse of learned movements and improved sample efficiency. The framework introduces intra-layer policies that guide the agent's transiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17751","kind":"arxiv","version":1},"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/2508.17751/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":"2508.17751","created_at":"2026-07-05T11:58:47.068406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17751v1","created_at":"2026-07-05T11:58:47.068406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17751","created_at":"2026-07-05T11:58:47.068406+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UHQO5GZC2AL","created_at":"2026-07-05T11:58:47.068406+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UHQO5GZC2AL4Z2V","created_at":"2026-07-05T11:58:47.068406+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UHQO5GZ","created_at":"2026-07-05T11:58:47.068406+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/2UHQO5GZC2AL4Z2VDVPN3QHREH","json":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH.json","graph_json":"https://pith.science/api/pith-number/2UHQO5GZC2AL4Z2VDVPN3QHREH/graph.json","events_json":"https://pith.science/api/pith-number/2UHQO5GZC2AL4Z2VDVPN3QHREH/events.json","paper":"https://pith.science/paper/2UHQO5GZ"},"agent_actions":{"view_html":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH","download_json":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH.json","view_paper":"https://pith.science/paper/2UHQO5GZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17751&json=true","fetch_graph":"https://pith.science/api/pith-number/2UHQO5GZC2AL4Z2VDVPN3QHREH/graph.json","fetch_events":"https://pith.science/api/pith-number/2UHQO5GZC2AL4Z2VDVPN3QHREH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH/action/storage_attestation","attest_author":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH/action/author_attestation","sign_citation":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH/action/citation_signature","submit_replication":"https://pith.science/pith/2UHQO5GZC2AL4Z2VDVPN3QHREH/action/replication_record"}},"created_at":"2026-07-05T11:58:47.068406+00:00","updated_at":"2026-07-05T11:58:47.068406+00:00"}