{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6JLZ64JBHPQLROAXJJT72OEONG","short_pith_number":"pith:6JLZ64JB","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"},"canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","source":{"kind":"arxiv","id":"1908.09184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09184","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09184v1","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09184","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"6JLZ64JBHPQL","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"6JLZ64JBHPQLROAX","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"6JLZ64JB","created_at":"2026-07-04T23:59:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6JLZ64JBHPQLROAXJJT72OEONG","target":"record","payload":{"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"},"canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","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"},"source_kind":"arxiv","source_id":"1908.09184","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWaCSoVolXCuhnvlG/4mkuq8vwEROudlfXi3R/BcjnsBNnMiDmoSSLgDlo7g+7wjucuMXiYQEcZd5sipc2xhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:34.977136Z"},"content_sha256":"cfae68490e196cae05e66d06f619fba5feec5fc40ecf2d530f13d958517c2457","schema_version":"1.0","event_id":"sha256:cfae68490e196cae05e66d06f619fba5feec5fc40ecf2d530f13d958517c2457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6JLZ64JBHPQLROAXJJT72OEONG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clBOpceHZpOkBhjy1/P12XFDSz+2KDX9EiXDU2PuSrZOx3fkNuyAD+C7WiuJX9NkljgtxRO/6N0L5lM393zhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:34.977520Z"},"content_sha256":"308f6f4c268fa951e2edee474ba15f87d33be493042b3c18aa359006e9ccda52","schema_version":"1.0","event_id":"sha256:308f6f4c268fa951e2edee474ba15f87d33be493042b3c18aa359006e9ccda52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/bundle.json","state_url":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JLZ64JBHPQLROAXJJT72OEONG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:06:34Z","links":{"resolver":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG","bundle":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/bundle.json","state":"https://pith.science/pith/6JLZ64JBHPQLROAXJJT72OEONG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JLZ64JBHPQLROAXJJT72OEONG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6JLZ64JBHPQLROAXJJT72OEONG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eb8bfda04d717015a38e15408ff235fedb675a9d652224d9238670c8bcecaf2f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2019-08-24T18:36:17Z","title_canon_sha256":"0723b44c71363c74b43e87cbe2979bafec15af5bb6ec57549b24b38dfc7a9989"},"schema_version":"1.0","source":{"id":"1908.09184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09184","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09184v1","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09184","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"6JLZ64JBHPQL","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"6JLZ64JBHPQLROAX","created_at":"2026-07-04T23:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"6JLZ64JB","created_at":"2026-07-04T23:59:37Z"}],"graph_snapshots":[{"event_id":"sha256:308f6f4c268fa951e2edee474ba15f87d33be493042b3c18aa359006e9ccda52","target":"graph","created_at":"2026-07-04T23:59:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.09184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2019-08-24T18:36:17Z","title":"Universal Policies to Learn Them All"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09184","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cfae68490e196cae05e66d06f619fba5feec5fc40ecf2d530f13d958517c2457","target":"record","created_at":"2026-07-04T23:59:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eb8bfda04d717015a38e15408ff235fedb675a9d652224d9238670c8bcecaf2f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2019-08-24T18:36:17Z","title_canon_sha256":"0723b44c71363c74b43e87cbe2979bafec15af5bb6ec57549b24b38dfc7a9989"},"schema_version":"1.0","source":{"id":"1908.09184","kind":"arxiv","version":1}},"canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2579f71213be0b8b8174a67fd388e699fc41283d8e304fa9cd98baf419bd818","first_computed_at":"2026-07-04T23:59:37.406655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:37.406655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oxFYOigZyVsmp1qxSQnu8jKBfZp0aFdmlZCKK/0AyPh3uJ0AkyDE4H2UefNw+CyhhGft0yvDS4L9HwonItV4Dg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:37.407092Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.09184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfae68490e196cae05e66d06f619fba5feec5fc40ecf2d530f13d958517c2457","sha256:308f6f4c268fa951e2edee474ba15f87d33be493042b3c18aa359006e9ccda52"],"state_sha256":"8eb8b63e13bc05fe3327d0d52514ec555d720f422d2aaa8092a6696966c68ffa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wa0xRQfJ8k2evnSbhu9LGdBTbCu7pYmcoo6f0QpBVdkM9yyHlD+fpzSAjpXVgtBzo5mYtz5fGQrPTq4RPO42Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:06:34.979432Z","bundle_sha256":"8cb19022a43ddbe7b7eab3a35401d3c416c3d7e3c1bbec67927c926364a61a1e"}}