{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FA6JY4XPHKPX2KXNRGEZSYV6OF","short_pith_number":"pith:FA6JY4XP","canonical_record":{"source":{"id":"2507.09989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T07:16:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"ed105718d2fd78b2178139fcb4c1dd3078bdc2982cddf4e2cd2086ea52e0fa97","abstract_canon_sha256":"3231031a77d222fd22fa2567f8d31f761d32807f43f290e7de7e4324b92d69b6"},"schema_version":"1.0"},"canonical_sha256":"283c9c72ef3a9f7d2aed89899962be7156908f54fb6ea60341e1e4ba6e026abc","source":{"kind":"arxiv","id":"2507.09989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09989","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09989v1","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09989","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_12","alias_value":"FA6JY4XPHKPX","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_16","alias_value":"FA6JY4XPHKPX2KXN","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_8","alias_value":"FA6JY4XP","created_at":"2026-07-05T11:36:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FA6JY4XPHKPX2KXNRGEZSYV6OF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T07:16:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"ed105718d2fd78b2178139fcb4c1dd3078bdc2982cddf4e2cd2086ea52e0fa97","abstract_canon_sha256":"3231031a77d222fd22fa2567f8d31f761d32807f43f290e7de7e4324b92d69b6"},"schema_version":"1.0"},"canonical_sha256":"283c9c72ef3a9f7d2aed89899962be7156908f54fb6ea60341e1e4ba6e026abc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:43.345975Z","signature_b64":"Rd8JGkEjXDZkKDTb0NPZFHtH1tEWC54Rgq70P3viMXush7EKSJg/AGzxlBXX4uAqBrOW/3kBLG+VWuzNSPz6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"283c9c72ef3a9f7d2aed89899962be7156908f54fb6ea60341e1e4ba6e026abc","last_reissued_at":"2026-07-05T11:36:43.345446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:43.345446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09989","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":"2026-07-05T11:36:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xcpjOX24Lj59Prt1y7+EcJRF0CS0RXVf6NZfIwFzKHsgGUlkFoKD/wQO/pF6F762prK3LpA0vm9neoDV02KDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:44:25.436556Z"},"content_sha256":"7e247e323818f3c75c0a085014316c393beea3d814e3f5a67644bf17aafefae9","schema_version":"1.0","event_id":"sha256:7e247e323818f3c75c0a085014316c393beea3d814e3f5a67644bf17aafefae9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FA6JY4XPHKPX2KXNRGEZSYV6OF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Sheng Han, Shuo Wang, Xiaoyang Yu, Youfang Lin","submitted_at":"2025-07-14T07:16:01Z","abstract_excerpt":"In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential update scheme, which requires independent learning with No Parameter-sharing (NoPS). However, heterogeneous MARL generally requires Partial Parameter-sharing (ParPS) based on agent grouping to achieve high cooperative performance. Our experiments prove that directly combining ParPS with the sequential update scheme leads to the policy updating baseline drift problem, thereby failin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09989","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/2507.09989/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":"2026-07-05T11:36:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGyc60BdGw8RvKW8+T5J3BctQ7Siei5BvoUnFEEmFDwk/xB/YPjov3C4KlS7UNcnHk3pRXDvncFHYmBjvzvvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:44:25.437105Z"},"content_sha256":"d2cd0008e8c1193017fcc669b0f60b524375a96197c426290c2eae97d6265f4b","schema_version":"1.0","event_id":"sha256:d2cd0008e8c1193017fcc669b0f60b524375a96197c426290c2eae97d6265f4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/bundle.json","state_url":"https://pith.science/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/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":"2026-08-08T19:44:25Z","links":{"resolver":"https://pith.science/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF","bundle":"https://pith.science/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/bundle.json","state":"https://pith.science/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FA6JY4XPHKPX2KXNRGEZSYV6OF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FA6JY4XPHKPX2KXNRGEZSYV6OF","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":"3231031a77d222fd22fa2567f8d31f761d32807f43f290e7de7e4324b92d69b6","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T07:16:01Z","title_canon_sha256":"ed105718d2fd78b2178139fcb4c1dd3078bdc2982cddf4e2cd2086ea52e0fa97"},"schema_version":"1.0","source":{"id":"2507.09989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09989","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09989v1","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09989","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_12","alias_value":"FA6JY4XPHKPX","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_16","alias_value":"FA6JY4XPHKPX2KXN","created_at":"2026-07-05T11:36:43Z"},{"alias_kind":"pith_short_8","alias_value":"FA6JY4XP","created_at":"2026-07-05T11:36:43Z"}],"graph_snapshots":[{"event_id":"sha256:d2cd0008e8c1193017fcc669b0f60b524375a96197c426290c2eae97d6265f4b","target":"graph","created_at":"2026-07-05T11:36:43Z","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/2507.09989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential update scheme, which requires independent learning with No Parameter-sharing (NoPS). However, heterogeneous MARL generally requires Partial Parameter-sharing (ParPS) based on agent grouping to achieve high cooperative performance. Our experiments prove that directly combining ParPS with the sequential update scheme leads to the policy updating baseline drift problem, thereby failin","authors_text":"Sheng Han, Shuo Wang, Xiaoyang Yu, Youfang Lin","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T07:16:01Z","title":"Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09989","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":"sha256:7e247e323818f3c75c0a085014316c393beea3d814e3f5a67644bf17aafefae9","target":"record","created_at":"2026-07-05T11:36:43Z","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":"3231031a77d222fd22fa2567f8d31f761d32807f43f290e7de7e4324b92d69b6","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T07:16:01Z","title_canon_sha256":"ed105718d2fd78b2178139fcb4c1dd3078bdc2982cddf4e2cd2086ea52e0fa97"},"schema_version":"1.0","source":{"id":"2507.09989","kind":"arxiv","version":1}},"canonical_sha256":"283c9c72ef3a9f7d2aed89899962be7156908f54fb6ea60341e1e4ba6e026abc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"283c9c72ef3a9f7d2aed89899962be7156908f54fb6ea60341e1e4ba6e026abc","first_computed_at":"2026-07-05T11:36:43.345446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:43.345446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rd8JGkEjXDZkKDTb0NPZFHtH1tEWC54Rgq70P3viMXush7EKSJg/AGzxlBXX4uAqBrOW/3kBLG+VWuzNSPz6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:43.345975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e247e323818f3c75c0a085014316c393beea3d814e3f5a67644bf17aafefae9","sha256:d2cd0008e8c1193017fcc669b0f60b524375a96197c426290c2eae97d6265f4b"],"state_sha256":"6f1e0b92fadbbf33308c192b2e61659e1c714277adbde57d37fdce6fc9c15791"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vulf+p53j34mxrgrl6GrLs/QZgm5UIGxr1IK8dKgJ9DNrd4McrFcX4Fr3T4p/G9s8EIoiiD3+Atzls4B5yM0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:44:25.442289Z","bundle_sha256":"ae98c2c096baf6035044d00f111e62850fde8b1edfd2356c27a83c64ef9b5043"}}