{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4CPUSMKYD45JQ77PVHN3DPW2MM","short_pith_number":"pith:4CPUSMKY","schema_version":"1.0","canonical_sha256":"e09f4931581f3a987fefa9dbb1beda63304b58722e5d657f2210033a2326b502","source":{"kind":"arxiv","id":"1912.02368","version":3},"attestation_state":"computed","paper":{"title":"Inter-Level Cooperation in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Rahman Kreidieh, Alexandre M. Bayen, Brandon Trabucco, Glen Berseth, Samyak Parajuli, Sergey Levine","submitted_at":"2019-12-05T03:56:44Z","abstract_excerpt":"Hierarchies of temporally decoupled policies present a promising approach for enabling structured exploration in complex long-term planning problems. To fully achieve this approach an end-to-end training paradigm is needed. However, training these multi-level policies has had limited success due to challenges arising from interactions between the goal-assigning and goal-achieving levels within a hierarchy. In this article, we consider the policy optimization process as a multi-agent process. This allows us to draw on connections between communication and cooperation in multi-agent RL, and demo"},"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":"1912.02368","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T03:56:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"dc755735a27bcde3263c5bf0e74ad28501326bedf8b32fb2bf912fa34b891995","abstract_canon_sha256":"8951b223c6aadb4d9c6d5145851ca27741266239256ade80120979c320506cb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:01.855635Z","signature_b64":"k9ahcJAXT6IBWG1KJoL7GeYgm3f3FgNSKk9QiVbiMPCmxa5U5rBJWhK0i4sbmmsOXSJ3twdxVe3Zfb3B+IRkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e09f4931581f3a987fefa9dbb1beda63304b58722e5d657f2210033a2326b502","last_reissued_at":"2026-07-05T03:33:01.855154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:01.855154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inter-Level Cooperation in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Rahman Kreidieh, Alexandre M. Bayen, Brandon Trabucco, Glen Berseth, Samyak Parajuli, Sergey Levine","submitted_at":"2019-12-05T03:56:44Z","abstract_excerpt":"Hierarchies of temporally decoupled policies present a promising approach for enabling structured exploration in complex long-term planning problems. To fully achieve this approach an end-to-end training paradigm is needed. However, training these multi-level policies has had limited success due to challenges arising from interactions between the goal-assigning and goal-achieving levels within a hierarchy. In this article, we consider the policy optimization process as a multi-agent process. This allows us to draw on connections between communication and cooperation in multi-agent RL, and demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02368","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/1912.02368/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":"1912.02368","created_at":"2026-07-05T03:33:01.855204+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.02368v3","created_at":"2026-07-05T03:33:01.855204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02368","created_at":"2026-07-05T03:33:01.855204+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CPUSMKYD45J","created_at":"2026-07-05T03:33:01.855204+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CPUSMKYD45JQ77P","created_at":"2026-07-05T03:33:01.855204+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CPUSMKY","created_at":"2026-07-05T03:33:01.855204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.09436","citing_title":"Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04356","citing_title":"Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundations","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM","json":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM.json","graph_json":"https://pith.science/api/pith-number/4CPUSMKYD45JQ77PVHN3DPW2MM/graph.json","events_json":"https://pith.science/api/pith-number/4CPUSMKYD45JQ77PVHN3DPW2MM/events.json","paper":"https://pith.science/paper/4CPUSMKY"},"agent_actions":{"view_html":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM","download_json":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM.json","view_paper":"https://pith.science/paper/4CPUSMKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.02368&json=true","fetch_graph":"https://pith.science/api/pith-number/4CPUSMKYD45JQ77PVHN3DPW2MM/graph.json","fetch_events":"https://pith.science/api/pith-number/4CPUSMKYD45JQ77PVHN3DPW2MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM/action/storage_attestation","attest_author":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM/action/author_attestation","sign_citation":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM/action/citation_signature","submit_replication":"https://pith.science/pith/4CPUSMKYD45JQ77PVHN3DPW2MM/action/replication_record"}},"created_at":"2026-07-05T03:33:01.855204+00:00","updated_at":"2026-07-05T03:33:01.855204+00:00"}