{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:X675ACVLJ4ZTVRTWEEWBPE3XVT","short_pith_number":"pith:X675ACVL","canonical_record":{"source":{"id":"2003.03433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-05T02:27:46Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d36e19aa5dd14209dd0211f8b0d465c38dd8ee04f44cd6fc0f4acdec7fefebe4","abstract_canon_sha256":"4c688df2ddcff1281ea096736ec08ef0cad40d0bfdf3c1e20d332829b9abe65f"},"schema_version":"1.0"},"canonical_sha256":"bfbfd00aab4f333ac676212c179377ace88715b52422c722ad35f36a2fc61d99","source":{"kind":"arxiv","id":"2003.03433","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03433","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03433v1","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03433","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"X675ACVLJ4ZT","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"X675ACVLJ4ZTVRTW","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"X675ACVL","created_at":"2026-07-05T00:46:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:X675ACVLJ4ZTVRTWEEWBPE3XVT","target":"record","payload":{"canonical_record":{"source":{"id":"2003.03433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-05T02:27:46Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d36e19aa5dd14209dd0211f8b0d465c38dd8ee04f44cd6fc0f4acdec7fefebe4","abstract_canon_sha256":"4c688df2ddcff1281ea096736ec08ef0cad40d0bfdf3c1e20d332829b9abe65f"},"schema_version":"1.0"},"canonical_sha256":"bfbfd00aab4f333ac676212c179377ace88715b52422c722ad35f36a2fc61d99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:21.336067Z","signature_b64":"wOfbixtRBL61jXW2xOI5oHHqViao0C6G5TZWxHr3ekOSIgrazJxFlMYjDbzYCpfn8BXe8VfabIxuOYojOX6HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfbfd00aab4f333ac676212c179377ace88715b52422c722ad35f36a2fc61d99","last_reissued_at":"2026-07-05T00:46:21.335576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:21.335576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.03433","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":"2026-07-05T00:46:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8etrNscSOvtTHSLUDmYDsR19Uvb+egd9/lJbcoYJzCq0UjrqJbTg9FBlvTk9d0vZJVnazFHAXJCdbJWknOSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T10:15:56.858219Z"},"content_sha256":"d33472a1f1cc542e83dbe81f14ef54095e146d37ec68ac754b56fc75615d070f","schema_version":"1.0","event_id":"sha256:d33472a1f1cc542e83dbe81f14ef54095e146d37ec68ac754b56fc75615d070f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:X675ACVLJ4ZTVRTWEEWBPE3XVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Hangyu Mao, Zhen Xiao, Zhibo Gong","submitted_at":"2020-03-05T02:27:46Z","abstract_excerpt":"In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem. The global reward signal assigns the same global reward to all agents without distinguishing their contributions, while the local reward signal provides different local rewards to each agent based solely on individual behavior. Both of the two reward assignment approaches have some shortcomings: the former might encourage lazy agents, while the latter might produce selfish agents.\n  In this paper, we study reward design problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03433","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/2003.03433/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":"2026-07-05T00:46:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IHnWoSPwzT15mm7xNNzC3uYO4ehZ8O+RMi/AufdpeoKFSkKRRPyYjgy4fS8dFZRpeFcwTX014Cb2XP+hTqBGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T10:15:56.858610Z"},"content_sha256":"e1113552a2382c8ee63d301a9f0fde619267bdc863ed9f70544b19093bdb8b09","schema_version":"1.0","event_id":"sha256:e1113552a2382c8ee63d301a9f0fde619267bdc863ed9f70544b19093bdb8b09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/bundle.json","state_url":"https://pith.science/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/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":"2026-07-10T10:15:56Z","links":{"resolver":"https://pith.science/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT","bundle":"https://pith.science/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/bundle.json","state":"https://pith.science/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X675ACVLJ4ZTVRTWEEWBPE3XVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X675ACVLJ4ZTVRTWEEWBPE3XVT","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":"4c688df2ddcff1281ea096736ec08ef0cad40d0bfdf3c1e20d332829b9abe65f","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-05T02:27:46Z","title_canon_sha256":"d36e19aa5dd14209dd0211f8b0d465c38dd8ee04f44cd6fc0f4acdec7fefebe4"},"schema_version":"1.0","source":{"id":"2003.03433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03433","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03433v1","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03433","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"X675ACVLJ4ZT","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"X675ACVLJ4ZTVRTW","created_at":"2026-07-05T00:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"X675ACVL","created_at":"2026-07-05T00:46:21Z"}],"graph_snapshots":[{"event_id":"sha256:e1113552a2382c8ee63d301a9f0fde619267bdc863ed9f70544b19093bdb8b09","target":"graph","created_at":"2026-07-05T00:46:21Z","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/2003.03433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem. The global reward signal assigns the same global reward to all agents without distinguishing their contributions, while the local reward signal provides different local rewards to each agent based solely on individual behavior. Both of the two reward assignment approaches have some shortcomings: the former might encourage lazy agents, while the latter might produce selfish agents.\n  In this paper, we study reward design problem","authors_text":"Hangyu Mao, Zhen Xiao, Zhibo Gong","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-05T02:27:46Z","title":"Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03433","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:d33472a1f1cc542e83dbe81f14ef54095e146d37ec68ac754b56fc75615d070f","target":"record","created_at":"2026-07-05T00:46:21Z","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":"4c688df2ddcff1281ea096736ec08ef0cad40d0bfdf3c1e20d332829b9abe65f","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-05T02:27:46Z","title_canon_sha256":"d36e19aa5dd14209dd0211f8b0d465c38dd8ee04f44cd6fc0f4acdec7fefebe4"},"schema_version":"1.0","source":{"id":"2003.03433","kind":"arxiv","version":1}},"canonical_sha256":"bfbfd00aab4f333ac676212c179377ace88715b52422c722ad35f36a2fc61d99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfbfd00aab4f333ac676212c179377ace88715b52422c722ad35f36a2fc61d99","first_computed_at":"2026-07-05T00:46:21.335576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:21.335576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wOfbixtRBL61jXW2xOI5oHHqViao0C6G5TZWxHr3ekOSIgrazJxFlMYjDbzYCpfn8BXe8VfabIxuOYojOX6HCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:21.336067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d33472a1f1cc542e83dbe81f14ef54095e146d37ec68ac754b56fc75615d070f","sha256:e1113552a2382c8ee63d301a9f0fde619267bdc863ed9f70544b19093bdb8b09"],"state_sha256":"80124011202d569a7b690c3fff69a799c467eeaa7ed60fbe500add662cf8d779"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6x2gUqewoFcl7Ffu6GbJjG07vkdo/IR898dV7ZyVx5JPVmRzY8pNWnW5UPoWaAzR13nJ/F/hRcfvkVCb3KxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T10:15:56.860626Z","bundle_sha256":"6f9958ad5ccf62fe44283c9f2612219664d0f916e6e86abbe877d23431b4e004"}}