{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MHTHYDRIY6TOZ5K3STZ2OT42AY","short_pith_number":"pith:MHTHYDRI","canonical_record":{"source":{"id":"2110.00096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8eddf0632c8e45e24f498e6494e16bc9b8e0f87cf548d7a952a16297d4f39622","abstract_canon_sha256":"3ce18befaede49a9bab4e3ae9bf2de0a996feeee2af6d4232a0e4fd91fb6015e"},"schema_version":"1.0"},"canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","source":{"kind":"arxiv","id":"2110.00096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00096","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00096v1","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00096","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"MHTHYDRIY6TO","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"MHTHYDRIY6TOZ5K3","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"MHTHYDRI","created_at":"2026-07-05T03:19:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MHTHYDRIY6TOZ5K3STZ2OT42AY","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8eddf0632c8e45e24f498e6494e16bc9b8e0f87cf548d7a952a16297d4f39622","abstract_canon_sha256":"3ce18befaede49a9bab4e3ae9bf2de0a996feeee2af6d4232a0e4fd91fb6015e"},"schema_version":"1.0"},"canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:25.555428Z","signature_b64":"JUbv/REGriYQJ2dzXXoL8Vob8qQ/WXMSMpQNq8QxV5UFidN2EtJo6XQWZeJTU19m8WmyeUgT/3329jN3BcXVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","last_reissued_at":"2026-07-05T03:19:25.554938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:25.554938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00096","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":"2026-07-05T03:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v919FC/AjHAnVPcrnaPerr7tpsdWuWCvUTVw9v1MWSb1FOzO44B1UrAXxMVZ0kzc+Fvdx+SGqv7Cw5ELJV3rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:00:36.304505Z"},"content_sha256":"e875e6aea57461c03ba291ca6cc73eefc7f92823a755f4ffff0e74dfea49f363","schema_version":"1.0","event_id":"sha256:e875e6aea57461c03ba291ca6cc73eefc7f92823a755f4ffff0e74dfea49f363"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MHTHYDRIY6TOZ5K3STZ2OT42AY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Guannan Qu, Jueming Hu, Weichang Wang, Yongming Liu, Yutian Pang, Zhe Xu","submitted_at":"2021-09-30T21:41:55Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward functions. We study the graph-based Markov Decision Process (MDP) where the dynamics of neighboring agents are coupled. We use a reward machine (RM) to encode each agent's task and expose reward function internal structures. RM has the capacity to describe high-level knowledge and encode non-Markovian reward functions. We propose a decentralized learning algorit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00096","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/2110.00096/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":"2026-07-05T03:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d+27GKQ0SJP8k4DrKpV6GebYQhNlDsC+6AbbBHAzqqHO3txpCWdeZQQMgF8mSTQY1JLTY07t7npfoI9owYJTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:00:36.305544Z"},"content_sha256":"74272d7e4d9ec277b4199cf1cf9394b344f557be3b8019461369f261e72586dd","schema_version":"1.0","event_id":"sha256:74272d7e4d9ec277b4199cf1cf9394b344f557be3b8019461369f261e72586dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/bundle.json","state_url":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/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":"2026-08-20T15:00:36Z","links":{"resolver":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY","bundle":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/bundle.json","state":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MHTHYDRIY6TOZ5K3STZ2OT42AY","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":"3ce18befaede49a9bab4e3ae9bf2de0a996feeee2af6d4232a0e4fd91fb6015e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","title_canon_sha256":"8eddf0632c8e45e24f498e6494e16bc9b8e0f87cf548d7a952a16297d4f39622"},"schema_version":"1.0","source":{"id":"2110.00096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00096","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00096v1","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00096","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"MHTHYDRIY6TO","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"MHTHYDRIY6TOZ5K3","created_at":"2026-07-05T03:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"MHTHYDRI","created_at":"2026-07-05T03:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:74272d7e4d9ec277b4199cf1cf9394b344f557be3b8019461369f261e72586dd","target":"graph","created_at":"2026-07-05T03:19:25Z","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/2110.00096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward functions. We study the graph-based Markov Decision Process (MDP) where the dynamics of neighboring agents are coupled. We use a reward machine (RM) to encode each agent's task and expose reward function internal structures. RM has the capacity to describe high-level knowledge and encode non-Markovian reward functions. We propose a decentralized learning algorit","authors_text":"Guannan Qu, Jueming Hu, Weichang Wang, Yongming Liu, Yutian Pang, Zhe Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00096","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:e875e6aea57461c03ba291ca6cc73eefc7f92823a755f4ffff0e74dfea49f363","target":"record","created_at":"2026-07-05T03:19:25Z","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":"3ce18befaede49a9bab4e3ae9bf2de0a996feeee2af6d4232a0e4fd91fb6015e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","title_canon_sha256":"8eddf0632c8e45e24f498e6494e16bc9b8e0f87cf548d7a952a16297d4f39622"},"schema_version":"1.0","source":{"id":"2110.00096","kind":"arxiv","version":1}},"canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","first_computed_at":"2026-07-05T03:19:25.554938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:25.554938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JUbv/REGriYQJ2dzXXoL8Vob8qQ/WXMSMpQNq8QxV5UFidN2EtJo6XQWZeJTU19m8WmyeUgT/3329jN3BcXVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:25.555428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e875e6aea57461c03ba291ca6cc73eefc7f92823a755f4ffff0e74dfea49f363","sha256:74272d7e4d9ec277b4199cf1cf9394b344f557be3b8019461369f261e72586dd"],"state_sha256":"16b7fb2f31602a8bf181305bf75f2b58af91995daa5f04dbb5184420086dfb11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTAVc4VZoVVp8uInXNjMac6GhSg4TnAcpdDKfc5F3ts1mR5b6ut1wD8X+mhy+JOajQpVxXjOc/W5dcj4/wqoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:00:36.310377Z","bundle_sha256":"ddcda302b62a51f0398a032623fdcb4b38958a71d2a0e327f0079ee0d8ce5300"}}