{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6JLZ64JBHPQLROAXJJT72OEONG","short_pith_number":"pith:6JLZ64JB","schema_version":"1.0","canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","source":{"kind":"arxiv","id":"1908.09184","version":1},"attestation_state":"computed","paper":{"title":"Universal Policies to Learn Them All","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","submitted_at":"2019-08-24T18:36:17Z","abstract_excerpt":"We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent reinforcement learning algorithm inspired by universal value function approximators that not only generalizes over state space but also over a set of different scenarios. Additionally, to prove our claim, we are introducing a challenging 2D multi-agent urban security environment where the learning agents are trying to protect a person from nearby bystanders in a "},"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":"1908.09184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2019-08-24T18:36:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0723b44c71363c74b43e87cbe2979bafec15af5bb6ec57549b24b38dfc7a9989","abstract_canon_sha256":"eb8bfda04d717015a38e15408ff235fedb675a9d652224d9238670c8bcecaf2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:37.407092Z","signature_b64":"oxFYOigZyVsmp1qxSQnu8jKBfZp0aFdmlZCKK/0AyPh3uJ0AkyDE4H2UefNw+CyhhGft0yvDS4L9HwonItV4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","last_reissued_at":"2026-07-04T23:59:37.406655Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:37.406655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Policies to Learn Them All","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","submitted_at":"2019-08-24T18:36:17Z","abstract_excerpt":"We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent reinforcement learning algorithm inspired by universal value function approximators that not only generalizes over state space but also over a set of different scenarios. Additionally, to prove our claim, we are introducing a challenging 2D multi-agent urban security environment where the learning agents are trying to protect a person from nearby bystanders in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09184","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/1908.09184/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":"1908.09184","created_at":"2026-07-04T23:59:37.406724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09184v1","created_at":"2026-07-04T23:59:37.406724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09184","created_at":"2026-07-04T23:59:37.406724+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JLZ64JBHPQL","created_at":"2026-07-04T23:59:37.406724+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JLZ64JBHPQLROAX","created_at":"2026-07-04T23:59:37.406724+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JLZ64JB","created_at":"2026-07-04T23:59:37.406724+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/6JLZ64JBHPQLROAXJJT72OEONG","json":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG.json","graph_json":"https://pith.science/api/pith-number/6JLZ64JBHPQLROAXJJT72OEONG/graph.json","events_json":"https://pith.science/api/pith-number/6JLZ64JBHPQLROAXJJT72OEONG/events.json","paper":"https://pith.science/paper/6JLZ64JB"},"agent_actions":{"view_html":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG","download_json":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG.json","view_paper":"https://pith.science/paper/6JLZ64JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09184&json=true","fetch_graph":"https://pith.science/api/pith-number/6JLZ64JBHPQLROAXJJT72OEONG/graph.json","fetch_events":"https://pith.science/api/pith-number/6JLZ64JBHPQLROAXJJT72OEONG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/action/storage_attestation","attest_author":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/action/author_attestation","sign_citation":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/action/citation_signature","submit_replication":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/action/replication_record"}},"created_at":"2026-07-04T23:59:37.406724+00:00","updated_at":"2026-07-04T23:59:37.406724+00:00"}