{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZI2VCQZ3TQI63BEUJDHWZL2XXS","short_pith_number":"pith:ZI2VCQZ3","canonical_record":{"source":{"id":"1706.05296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-16T14:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"ddd35dad0b591b55ce426fad78fb1945026a092bca13895d1f936c959bf4eb5e","abstract_canon_sha256":"471eefde333af8de058211a9aec266e746b62f024e1c235d8c0aa6074777cd37"},"schema_version":"1.0"},"canonical_sha256":"ca3551433b9c11ed849448cf6caf57bca32ea2bb1276f34d5f85be71d0d86b6a","source":{"kind":"arxiv","id":"1706.05296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05296","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05296v1","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05296","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2VCQZ3TQI6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2VCQZ3TQI63BEU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2VCQZ3","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZI2VCQZ3TQI63BEUJDHWZL2XXS","target":"record","payload":{"canonical_record":{"source":{"id":"1706.05296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-16T14:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"ddd35dad0b591b55ce426fad78fb1945026a092bca13895d1f936c959bf4eb5e","abstract_canon_sha256":"471eefde333af8de058211a9aec266e746b62f024e1c235d8c0aa6074777cd37"},"schema_version":"1.0"},"canonical_sha256":"ca3551433b9c11ed849448cf6caf57bca32ea2bb1276f34d5f85be71d0d86b6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:14.173364Z","signature_b64":"d1Li3pz5Wxf5KEy7PklpztMFalwF9vvwVokVmxySRaY0WGS0H+UJvxHEzL2wUBcyvfm4h+hHIL64molm/pa4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3551433b9c11ed849448cf6caf57bca32ea2bb1276f34d5f85be71d0d86b6a","last_reissued_at":"2026-05-18T00:42:14.172761Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:14.172761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.05296","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":"2026-05-18T00:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9OANUoIolsi15eQk+Qk0BMp2EBtzMfs3Gq7to3jWbRpcODg/Fgup6yqInJhNLyCpI+vRYhIhDs45U+8jwv3yDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:30:32.198687Z"},"content_sha256":"9eb614dc0d4363940fcb5318e5e0c1eb146558e0b36733d93f536afe3f9d6f6c","schema_version":"1.0","event_id":"sha256:9eb614dc0d4363940fcb5318e5e0c1eb146558e0b36733d93f536afe3f9d6f6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZI2VCQZ3TQI63BEUJDHWZL2XXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Audrunas Gruslys, Guy Lever, Joel Z. Leibo, Karl Tuyls, Marc Lanctot, Max Jaderberg, Nicolas Sonnerat, Peter Sunehag, Thore Graepel, Vinicius Zambaldi, Wojciech Marian Czarnecki","submitted_at":"2017-06-16T14:47:21Z","abstract_excerpt":"We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and decentralized approaches, we find the problem of spurious rewards and a phenomenon we call the \"lazy agent\" problem, which arises due to partial observability. We address these problems by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05296","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":""},"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":"2026-05-18T00:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RebRjoqmSkn3VgGdv0+e1azVgpPzAtmcZc/5cPv2L8YYI7KtBaQG36z7986C3Ks/MdaxQJRJfxxiRh/ziddIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:30:32.199036Z"},"content_sha256":"11093f6718051889c5c592f9180b44e652f31a17787791ec0663ec4e9db99de8","schema_version":"1.0","event_id":"sha256:11093f6718051889c5c592f9180b44e652f31a17787791ec0663ec4e9db99de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/bundle.json","state_url":"https://pith.science/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/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":"2026-06-01T12:30:32Z","links":{"resolver":"https://pith.science/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS","bundle":"https://pith.science/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/bundle.json","state":"https://pith.science/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZI2VCQZ3TQI63BEUJDHWZL2XXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZI2VCQZ3TQI63BEUJDHWZL2XXS","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":"471eefde333af8de058211a9aec266e746b62f024e1c235d8c0aa6074777cd37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-16T14:47:21Z","title_canon_sha256":"ddd35dad0b591b55ce426fad78fb1945026a092bca13895d1f936c959bf4eb5e"},"schema_version":"1.0","source":{"id":"1706.05296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05296","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05296v1","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05296","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2VCQZ3TQI6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2VCQZ3TQI63BEU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2VCQZ3","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:11093f6718051889c5c592f9180b44e652f31a17787791ec0663ec4e9db99de8","target":"graph","created_at":"2026-05-18T00:42:14Z","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"},"paper":{"abstract_excerpt":"We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and decentralized approaches, we find the problem of spurious rewards and a phenomenon we call the \"lazy agent\" problem, which arises due to partial observability. We address these problems by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions.","authors_text":"Audrunas Gruslys, Guy Lever, Joel Z. Leibo, Karl Tuyls, Marc Lanctot, Max Jaderberg, Nicolas Sonnerat, Peter Sunehag, Thore Graepel, Vinicius Zambaldi, Wojciech Marian Czarnecki","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-16T14:47:21Z","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05296","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":"sha256:9eb614dc0d4363940fcb5318e5e0c1eb146558e0b36733d93f536afe3f9d6f6c","target":"record","created_at":"2026-05-18T00:42:14Z","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":"471eefde333af8de058211a9aec266e746b62f024e1c235d8c0aa6074777cd37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-16T14:47:21Z","title_canon_sha256":"ddd35dad0b591b55ce426fad78fb1945026a092bca13895d1f936c959bf4eb5e"},"schema_version":"1.0","source":{"id":"1706.05296","kind":"arxiv","version":1}},"canonical_sha256":"ca3551433b9c11ed849448cf6caf57bca32ea2bb1276f34d5f85be71d0d86b6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca3551433b9c11ed849448cf6caf57bca32ea2bb1276f34d5f85be71d0d86b6a","first_computed_at":"2026-05-18T00:42:14.172761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:14.172761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d1Li3pz5Wxf5KEy7PklpztMFalwF9vvwVokVmxySRaY0WGS0H+UJvxHEzL2wUBcyvfm4h+hHIL64molm/pa4Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:14.173364Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.05296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9eb614dc0d4363940fcb5318e5e0c1eb146558e0b36733d93f536afe3f9d6f6c","sha256:11093f6718051889c5c592f9180b44e652f31a17787791ec0663ec4e9db99de8"],"state_sha256":"3ff2e9038bb4d0c8480525eb1f2a4c7678855a480b3ee6aff8ba0f6c2308fb32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7CI8vqlCH160ZK3P02U+OZ5pi2NbUnvALbC3nKMMmnP4fBBSICCRAl+sXPyjcu8Q/ZxPn1ZLqfZFf63IyzRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:30:32.201114Z","bundle_sha256":"84857c33f8a8915b8e3dcb9399228a6333f2778d2415651ad6dbbb8718574348"}}