{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6C4CZR43CUOEDDEDPYZ2IN66LQ","short_pith_number":"pith:6C4CZR43","canonical_record":{"source":{"id":"2408.04295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-08T08:18:05Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"86292562e473cf6bb0bca9c5f5c0b5d5f25e9b73b8df57bff7499fc8ef4faebe","abstract_canon_sha256":"00452bd8e05118b77da3df846df8e0afe7dcee2567da6c2cdb2c0ee696ad545b"},"schema_version":"1.0"},"canonical_sha256":"f0b82cc79b151c418c837e33a437de5c1746c3d1f9a241bca5a1957dc5c8b324","source":{"kind":"arxiv","id":"2408.04295","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04295","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04295v3","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04295","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"6C4CZR43CUOE","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"6C4CZR43CUOEDDED","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"6C4CZR43","created_at":"2026-07-05T10:10:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6C4CZR43CUOEDDEDPYZ2IN66LQ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-08T08:18:05Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"86292562e473cf6bb0bca9c5f5c0b5d5f25e9b73b8df57bff7499fc8ef4faebe","abstract_canon_sha256":"00452bd8e05118b77da3df846df8e0afe7dcee2567da6c2cdb2c0ee696ad545b"},"schema_version":"1.0"},"canonical_sha256":"f0b82cc79b151c418c837e33a437de5c1746c3d1f9a241bca5a1957dc5c8b324","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:42.420544Z","signature_b64":"5w3rVeLNjSu021SfX5EcU1jQH+DkpPmpsgGw28/bZlb3V+FERYMgylyJxobNFIpVuZ0CMQ/Ua2iR/uZZMFzbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0b82cc79b151c418c837e33a437de5c1746c3d1f9a241bca5a1957dc5c8b324","last_reissued_at":"2026-07-05T10:10:42.419890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:42.419890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04295","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VcI8LpC57wx1hh1qRHkET7fzkFezm0W5JBXwar+NLHRt7uSPkx9I/+rcrYzr9AFJUbgTwPipH73IfvOlojslAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:15.391999Z"},"content_sha256":"ee98dbeafe11bca83821655d7b28e4ed7f78d1b28bd20e3b428b931b5f8dd84d","schema_version":"1.0","event_id":"sha256:ee98dbeafe11bca83821655d7b28e4ed7f78d1b28bd20e3b428b931b5f8dd84d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6C4CZR43CUOEDDEDPYZ2IN66LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Aditya Kapoor, Benjamin Freed, Howie Choset, Jeff Schneider","submitted_at":"2024-08-08T08:18:05Z","abstract_excerpt":"Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the sheer difficulty in ascribing credit to individual agents' actions scales poorly with team size. In this paper, we propose a multi-agent reinforcement learning algorithm that adapts recent developments in credit assignment to improve upon MAPPO. Our approach leverages partial reward decoupling (PRD), which uses a learned attention mechanism to estimate which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04295","kind":"arxiv","version":3},"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/2408.04295/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":"2026-07-05T10:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aExKIZ7Sj2sgP0hIN+G1HSI8e6AhRIb3n2oMmRaGGgjuM6+TD1TGLKwa4xgulAeAEZHQNf5oc1e5Dx+j5SUZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:15.392392Z"},"content_sha256":"c50ba9cc130d64810556251a54398242166ed186d38657c1e59ce667ff150fb3","schema_version":"1.0","event_id":"sha256:c50ba9cc130d64810556251a54398242166ed186d38657c1e59ce667ff150fb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/bundle.json","state_url":"https://pith.science/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/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":"2026-07-07T12:43:15Z","links":{"resolver":"https://pith.science/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ","bundle":"https://pith.science/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/bundle.json","state":"https://pith.science/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6C4CZR43CUOEDDEDPYZ2IN66LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6C4CZR43CUOEDDEDPYZ2IN66LQ","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":"00452bd8e05118b77da3df846df8e0afe7dcee2567da6c2cdb2c0ee696ad545b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-08T08:18:05Z","title_canon_sha256":"86292562e473cf6bb0bca9c5f5c0b5d5f25e9b73b8df57bff7499fc8ef4faebe"},"schema_version":"1.0","source":{"id":"2408.04295","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04295","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04295v3","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04295","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"6C4CZR43CUOE","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"6C4CZR43CUOEDDED","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"6C4CZR43","created_at":"2026-07-05T10:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:c50ba9cc130d64810556251a54398242166ed186d38657c1e59ce667ff150fb3","target":"graph","created_at":"2026-07-05T10:10:42Z","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/2408.04295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the sheer difficulty in ascribing credit to individual agents' actions scales poorly with team size. In this paper, we propose a multi-agent reinforcement learning algorithm that adapts recent developments in credit assignment to improve upon MAPPO. Our approach leverages partial reward decoupling (PRD), which uses a learned attention mechanism to estimate which","authors_text":"Aditya Kapoor, Benjamin Freed, Howie Choset, Jeff Schneider","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-08T08:18:05Z","title":"Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04295","kind":"arxiv","version":3},"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:ee98dbeafe11bca83821655d7b28e4ed7f78d1b28bd20e3b428b931b5f8dd84d","target":"record","created_at":"2026-07-05T10:10:42Z","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":"00452bd8e05118b77da3df846df8e0afe7dcee2567da6c2cdb2c0ee696ad545b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-08T08:18:05Z","title_canon_sha256":"86292562e473cf6bb0bca9c5f5c0b5d5f25e9b73b8df57bff7499fc8ef4faebe"},"schema_version":"1.0","source":{"id":"2408.04295","kind":"arxiv","version":3}},"canonical_sha256":"f0b82cc79b151c418c837e33a437de5c1746c3d1f9a241bca5a1957dc5c8b324","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0b82cc79b151c418c837e33a437de5c1746c3d1f9a241bca5a1957dc5c8b324","first_computed_at":"2026-07-05T10:10:42.419890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:42.419890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5w3rVeLNjSu021SfX5EcU1jQH+DkpPmpsgGw28/bZlb3V+FERYMgylyJxobNFIpVuZ0CMQ/Ua2iR/uZZMFzbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:42.420544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04295","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee98dbeafe11bca83821655d7b28e4ed7f78d1b28bd20e3b428b931b5f8dd84d","sha256:c50ba9cc130d64810556251a54398242166ed186d38657c1e59ce667ff150fb3"],"state_sha256":"e105f9bb5c57846ecdc97b35a7d75032489ef373f0f78d391b27c60f45899533"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xk8yqia+wpVsc0IhuilTRzj0uK17tx11paebkb5qfXXFrY5WQAU10WhTGlgrMtiB+D9y1lhTt5l5K5JdYjwVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:43:15.394328Z","bundle_sha256":"6e2dace8c59d0fa9dd748dd2d6967a0897f40aab0247763d138ad959a750088b"}}