{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OYDVAEKRG627WSFXDRUQRNDEBJ","short_pith_number":"pith:OYDVAEKR","schema_version":"1.0","canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","source":{"kind":"arxiv","id":"1703.06182","version":4},"attestation_state":"computed","paper":{"title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Christopher Amato, Jason Pazis, John Vian, Jonathan P. How, Shayegan Omidshafiei","submitted_at":"2017-03-17T19:32:38Z","abstract_excerpt":"Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of mu"},"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":"1703.06182","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-17T19:32:38Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"e63964c3ee0b8048a0851a39365f7e1b88f03a9393ccd86152217e150242f5b5","abstract_canon_sha256":"e0416ca83c6c21aefdaf8bfe291e9397197640329773b7324715fa2b5a582f4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:30.842907Z","signature_b64":"EvjvAbmirUyg5XGax4jR2O9HfifnkzLVuZankXOP/anZ3S9Vm1ZFg7HJJDT21WuRLC83DSTXxuB9mSbBnxCeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760750115137b5fb48b71c6908b4640a4bccd2033042ac2c6143a1390c05276d","last_reissued_at":"2026-05-18T00:15:30.842398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:30.842398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Christopher Amato, Jason Pazis, John Vian, Jonathan P. How, Shayegan Omidshafiei","submitted_at":"2017-03-17T19:32:38Z","abstract_excerpt":"Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06182","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1703.06182","created_at":"2026-05-18T00:15:30.842484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06182v4","created_at":"2026-05-18T00:15:30.842484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06182","created_at":"2026-05-18T00:15:30.842484+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYDVAEKRG627","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYDVAEKRG627WSFX","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYDVAEKR","created_at":"2026-05-18T12:31:34.259226+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/OYDVAEKRG627WSFXDRUQRNDEBJ","json":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ.json","graph_json":"https://pith.science/api/pith-number/OYDVAEKRG627WSFXDRUQRNDEBJ/graph.json","events_json":"https://pith.science/api/pith-number/OYDVAEKRG627WSFXDRUQRNDEBJ/events.json","paper":"https://pith.science/paper/OYDVAEKR"},"agent_actions":{"view_html":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ","download_json":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ.json","view_paper":"https://pith.science/paper/OYDVAEKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06182&json=true","fetch_graph":"https://pith.science/api/pith-number/OYDVAEKRG627WSFXDRUQRNDEBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OYDVAEKRG627WSFXDRUQRNDEBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/action/storage_attestation","attest_author":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/action/author_attestation","sign_citation":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/action/citation_signature","submit_replication":"https://pith.science/pith/OYDVAEKRG627WSFXDRUQRNDEBJ/action/replication_record"}},"created_at":"2026-05-18T00:15:30.842484+00:00","updated_at":"2026-05-18T00:15:30.842484+00:00"}