{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VP3L6TCCCGQ27MK4BEJEJ7PXHQ","short_pith_number":"pith:VP3L6TCC","canonical_record":{"source":{"id":"1901.08492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-01-24T16:44:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eaec0e58ec194ab91a19d2131c9077b357364fd8dab1bb201a6686d2c346662e","abstract_canon_sha256":"9d238543c141bf2b8b53ad9024f6ee9265e2328f4e6c1a5c613bffd51d47e185"},"schema_version":"1.0"},"canonical_sha256":"abf6bf4c4211a1afb15c091244fdf73c3975da64ea0fdd7d908224aaa26729b5","source":{"kind":"arxiv","id":"1901.08492","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08492","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08492v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08492","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"VP3L6TCCCGQ2","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VP3L6TCCCGQ27MK4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VP3L6TCC","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VP3L6TCCCGQ27MK4BEJEJ7PXHQ","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-01-24T16:44:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eaec0e58ec194ab91a19d2131c9077b357364fd8dab1bb201a6686d2c346662e","abstract_canon_sha256":"9d238543c141bf2b8b53ad9024f6ee9265e2328f4e6c1a5c613bffd51d47e185"},"schema_version":"1.0"},"canonical_sha256":"abf6bf4c4211a1afb15c091244fdf73c3975da64ea0fdd7d908224aaa26729b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:33.634651Z","signature_b64":"NlPwoel5EEB0c7exFypMkJfRW5a81CUZpAL1LSjVw0YbrijcpfOSKVoQnFVZyWav5tPbGnwb3eebdsdtw0ePBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf6bf4c4211a1afb15c091244fdf73c3975da64ea0fdd7d908224aaa26729b5","last_reissued_at":"2026-05-17T23:55:33.634210Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:33.634210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08492","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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1D9dkr5upQSfYXgJAvB1IBVPpjrK7ehKzh4ogSbg0gNX13nQl0r6CrLK7JePAYsrZ6lon4cTGKt8mwv0GmkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:28:13.802502Z"},"content_sha256":"d042478f2aa12483b4b4f32bed8f8b10d8a8d8fdbc312caa82bd826cf7da9c1e","schema_version":"1.0","event_id":"sha256:d042478f2aa12483b4b4f32bed8f8b10d8a8d8fdbc312caa82bd826cf7da9c1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VP3L6TCCCGQ27MK4BEJEJ7PXHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Peter Dayan, Sanjeevan Ahilan","submitted_at":"2019-01-24T16:44:16Z","abstract_excerpt":"We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent Hierarchies (FMH). In this framework, a 'manager' agent, which is tasked with maximising the environmentally-determined reward function, learns to communicate subgoals to multiple, simultaneously-operating, 'worker' agents. Workers, which are rewarded for achieving managerial subgoals, take concurrent actions in the world. We outline the structure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08492","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":""},"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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsDUYOf1sAbtZ7C5sGjiFAHbrZhTS8WkresmAei6aYw6yOghKyPRGUhakB7Thc7Jiq5D7snQ3ZWqye1v9XVsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:28:13.803161Z"},"content_sha256":"c27f9a568a3b173d1cc70f3f8d2d61eee129afe42733fc2a8819800570e1d1a5","schema_version":"1.0","event_id":"sha256:c27f9a568a3b173d1cc70f3f8d2d61eee129afe42733fc2a8819800570e1d1a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/bundle.json","state_url":"https://pith.science/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/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":"2026-06-10T13:28:13Z","links":{"resolver":"https://pith.science/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ","bundle":"https://pith.science/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/bundle.json","state":"https://pith.science/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VP3L6TCCCGQ27MK4BEJEJ7PXHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VP3L6TCCCGQ27MK4BEJEJ7PXHQ","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":"9d238543c141bf2b8b53ad9024f6ee9265e2328f4e6c1a5c613bffd51d47e185","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-01-24T16:44:16Z","title_canon_sha256":"eaec0e58ec194ab91a19d2131c9077b357364fd8dab1bb201a6686d2c346662e"},"schema_version":"1.0","source":{"id":"1901.08492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08492","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08492v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08492","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"VP3L6TCCCGQ2","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VP3L6TCCCGQ27MK4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VP3L6TCC","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:c27f9a568a3b173d1cc70f3f8d2d61eee129afe42733fc2a8819800570e1d1a5","target":"graph","created_at":"2026-05-17T23:55:33Z","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"},"paper":{"abstract_excerpt":"We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent Hierarchies (FMH). In this framework, a 'manager' agent, which is tasked with maximising the environmentally-determined reward function, learns to communicate subgoals to multiple, simultaneously-operating, 'worker' agents. Workers, which are rewarded for achieving managerial subgoals, take concurrent actions in the world. We outline the structure","authors_text":"Peter Dayan, Sanjeevan Ahilan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-01-24T16:44:16Z","title":"Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08492","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:d042478f2aa12483b4b4f32bed8f8b10d8a8d8fdbc312caa82bd826cf7da9c1e","target":"record","created_at":"2026-05-17T23:55:33Z","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":"9d238543c141bf2b8b53ad9024f6ee9265e2328f4e6c1a5c613bffd51d47e185","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-01-24T16:44:16Z","title_canon_sha256":"eaec0e58ec194ab91a19d2131c9077b357364fd8dab1bb201a6686d2c346662e"},"schema_version":"1.0","source":{"id":"1901.08492","kind":"arxiv","version":1}},"canonical_sha256":"abf6bf4c4211a1afb15c091244fdf73c3975da64ea0fdd7d908224aaa26729b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abf6bf4c4211a1afb15c091244fdf73c3975da64ea0fdd7d908224aaa26729b5","first_computed_at":"2026-05-17T23:55:33.634210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:33.634210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NlPwoel5EEB0c7exFypMkJfRW5a81CUZpAL1LSjVw0YbrijcpfOSKVoQnFVZyWav5tPbGnwb3eebdsdtw0ePBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:33.634651Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d042478f2aa12483b4b4f32bed8f8b10d8a8d8fdbc312caa82bd826cf7da9c1e","sha256:c27f9a568a3b173d1cc70f3f8d2d61eee129afe42733fc2a8819800570e1d1a5"],"state_sha256":"37f4a38ff1133815e695db2c1680767afff97e13e300883fd6df1d13c5b76d58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRWEaCtZlE79dQiqkt0q7l+177sW9ffk9DyLISt+elD+q6HfeCCPp61sMPuPYXWf8crPlBsBk0/adOeL0PLOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T13:28:13.807234Z","bundle_sha256":"3144b72b883ee0fefbd0958e7d8c68c9a87e52543dfbe7b0815fe29d8fa3bab9"}}