{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2L4BPT6HXFNPAEQIRMUC5ZKPZX","short_pith_number":"pith:2L4BPT6H","canonical_record":{"source":{"id":"2003.10598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-24T00:55:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"40315619828f5713f38f08ad84181e9a7c8813d0525546848ab5c22d30d49c22","abstract_canon_sha256":"cba54c9d15f5da75e9205b843be50715048a7a0ead1927a974f2b82cfea8b997"},"schema_version":"1.0"},"canonical_sha256":"d2f817cfc7b95af012088b282ee54fcdde336918c13a1ab55ae5ed10f23a176f","source":{"kind":"arxiv","id":"2003.10598","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10598","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10598v1","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10598","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"2L4BPT6HXFNP","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"2L4BPT6HXFNPAEQI","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"2L4BPT6H","created_at":"2026-07-05T00:50:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2L4BPT6HXFNPAEQIRMUC5ZKPZX","target":"record","payload":{"canonical_record":{"source":{"id":"2003.10598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-24T00:55:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"40315619828f5713f38f08ad84181e9a7c8813d0525546848ab5c22d30d49c22","abstract_canon_sha256":"cba54c9d15f5da75e9205b843be50715048a7a0ead1927a974f2b82cfea8b997"},"schema_version":"1.0"},"canonical_sha256":"d2f817cfc7b95af012088b282ee54fcdde336918c13a1ab55ae5ed10f23a176f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:18.834473Z","signature_b64":"9vVHzGjnYwfuql0I63HcCUPLO5+scJ8aOjhqC3n9Od54fgquak+Qw/4RUtz/uiKybsp+GhgJvqVC4NvoM8L4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f817cfc7b95af012088b282ee54fcdde336918c13a1ab55ae5ed10f23a176f","last_reissued_at":"2026-07-05T00:50:18.834026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:18.834026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.10598","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":"2026-07-05T00:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PABsmzENx8o8+sHjAxmHKeow/6FDCz4vPYeJIKRKTEQOmsuNUAY16vqplLuOXz1cgHHXFzGuV9Q+sQB475bOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:13.940377Z"},"content_sha256":"05f74eef55cf36bd987415af1078fac32daa37004cc93d0e28ebd4d52543e5d0","schema_version":"1.0","event_id":"sha256:05f74eef55cf36bd987415af1078fac32daa37004cc93d0e28ebd4d52543e5d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2L4BPT6HXFNPAEQIRMUC5ZKPZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","submitted_at":"2020-03-24T00:55:37Z","abstract_excerpt":"Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed to either maximize the global reward of the team or the individual local rewards. The problem is exacerbated when either of the rewards is sparse leading to unstable learning. To address this problem, we present Decomposed Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG): a novel cooperative multi-agent reinforcement learning framework tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10598","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/2003.10598/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":"2026-07-05T00:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDb9EWgVGD6muU0laTcLPKIIIB2GpdQV5hcjEaIs+ph1302sycS4CPg9MiDrVDScQIirUZ8VWTtQ4Iy+tEYdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:13.940733Z"},"content_sha256":"58bbf2fe952792ca64364f80b15f1767c39c5ee1ea66c3e5c6e11486d46597e4","schema_version":"1.0","event_id":"sha256:58bbf2fe952792ca64364f80b15f1767c39c5ee1ea66c3e5c6e11486d46597e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/bundle.json","state_url":"https://pith.science/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/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":"2026-07-06T18:44:13Z","links":{"resolver":"https://pith.science/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX","bundle":"https://pith.science/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/bundle.json","state":"https://pith.science/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2L4BPT6HXFNPAEQIRMUC5ZKPZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2L4BPT6HXFNPAEQIRMUC5ZKPZX","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":"cba54c9d15f5da75e9205b843be50715048a7a0ead1927a974f2b82cfea8b997","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-24T00:55:37Z","title_canon_sha256":"40315619828f5713f38f08ad84181e9a7c8813d0525546848ab5c22d30d49c22"},"schema_version":"1.0","source":{"id":"2003.10598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10598","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10598v1","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10598","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"2L4BPT6HXFNP","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"2L4BPT6HXFNPAEQI","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"2L4BPT6H","created_at":"2026-07-05T00:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:58bbf2fe952792ca64364f80b15f1767c39c5ee1ea66c3e5c6e11486d46597e4","target":"graph","created_at":"2026-07-05T00:50:18Z","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/2003.10598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed to either maximize the global reward of the team or the individual local rewards. The problem is exacerbated when either of the rewards is sparse leading to unstable learning. To address this problem, we present Decomposed Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG): a novel cooperative multi-agent reinforcement learning framework tha","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-24T00:55:37Z","title":"Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10598","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":"sha256:05f74eef55cf36bd987415af1078fac32daa37004cc93d0e28ebd4d52543e5d0","target":"record","created_at":"2026-07-05T00:50:18Z","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":"cba54c9d15f5da75e9205b843be50715048a7a0ead1927a974f2b82cfea8b997","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-24T00:55:37Z","title_canon_sha256":"40315619828f5713f38f08ad84181e9a7c8813d0525546848ab5c22d30d49c22"},"schema_version":"1.0","source":{"id":"2003.10598","kind":"arxiv","version":1}},"canonical_sha256":"d2f817cfc7b95af012088b282ee54fcdde336918c13a1ab55ae5ed10f23a176f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2f817cfc7b95af012088b282ee54fcdde336918c13a1ab55ae5ed10f23a176f","first_computed_at":"2026-07-05T00:50:18.834026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:50:18.834026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9vVHzGjnYwfuql0I63HcCUPLO5+scJ8aOjhqC3n9Od54fgquak+Qw/4RUtz/uiKybsp+GhgJvqVC4NvoM8L4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:50:18.834473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.10598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f74eef55cf36bd987415af1078fac32daa37004cc93d0e28ebd4d52543e5d0","sha256:58bbf2fe952792ca64364f80b15f1767c39c5ee1ea66c3e5c6e11486d46597e4"],"state_sha256":"cbf3a8b95e7b9effadd8d8312be0c868c3145bf06ce5956c5b087af20c8750b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hDmZyAZ2VgdeMeV6aN4pXfENq4we9JCgkINa41NYICEh+Y5czkM0PagWAGhKJ/H6y14D3A0EzNh4scjkgMKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:44:13.942623Z","bundle_sha256":"5b69446a26f5d36c4585df10b7feeb3b0e1652b91d233b52731dcaf7943ab4db"}}