{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G4MEUVWSUMJX64HKAXITHITNMH","short_pith_number":"pith:G4MEUVWS","canonical_record":{"source":{"id":"2211.16068","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T10:22:55Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"abc6802590ff2f1b441aea76e04724199d6bf9ed629b77866ec89786d4f6c0b3","abstract_canon_sha256":"4fe0119c1feed4fae4967bd583e3d3f16d690331e1a90af9d538059dd7d0706d"},"schema_version":"1.0"},"canonical_sha256":"37184a56d2a3137f70ea05d133a26d61e5143e5e64ba8c8f71617a0d11c63075","source":{"kind":"arxiv","id":"2211.16068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16068","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16068v2","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16068","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"G4MEUVWSUMJX","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"G4MEUVWSUMJX64HK","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"G4MEUVWS","created_at":"2026-07-05T05:21:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G4MEUVWSUMJX64HKAXITHITNMH","target":"record","payload":{"canonical_record":{"source":{"id":"2211.16068","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T10:22:55Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"abc6802590ff2f1b441aea76e04724199d6bf9ed629b77866ec89786d4f6c0b3","abstract_canon_sha256":"4fe0119c1feed4fae4967bd583e3d3f16d690331e1a90af9d538059dd7d0706d"},"schema_version":"1.0"},"canonical_sha256":"37184a56d2a3137f70ea05d133a26d61e5143e5e64ba8c8f71617a0d11c63075","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:45.441534Z","signature_b64":"hnISwwOSp7NHDw3wq/H94zWEYsJFVt0uoOs6jKIzspxXG54w+IrlXGS/+WVWpTJiS3Rh/5WRmVfczukQpoiGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37184a56d2a3137f70ea05d133a26d61e5143e5e64ba8c8f71617a0d11c63075","last_reissued_at":"2026-07-05T05:21:45.441062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:45.441062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.16068","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceyzPlOHFEt5sAtZyQ2vLJu2RXmywNl8xi4Onf+qJxATP9W7G6Tm/jWAIUncJSwFOiHkERsk0/z/R9TDuYYyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:34:25.198283Z"},"content_sha256":"865a9750bdb15b0f82b3b5db826a57874af3c2b1c9ec62a2b396406af33804dc","schema_version":"1.0","event_id":"sha256:865a9750bdb15b0f82b3b5db826a57874af3c2b1c9ec62a2b396406af33804dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G4MEUVWSUMJX64HKAXITHITNMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Chuming Li, Jie Liu, Wanli Ouyang, Yaodong Yang, Yazhe Niu, Yinmin Zhang, Yuhong Wei, Yu Liu","submitted_at":"2022-11-29T10:22:55Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policies at the same time. Starting from first principle, in this paper, we manage to solve the non-stationarity problem by proposing bidirectional action-dependent Q-learning (ACE). Central to the development of ACE is the sequential decision-making process wherein only one agent is allowed to take action at one time. Within this process, each agent maximizes its value function given the actions taken by the preceding agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16068","kind":"arxiv","version":2},"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/2211.16068/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":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kykiOnyCZhOhQJwvHMOW48Z3te7lJe4jXNlQjm/sDoomvrdTogOPElPLtrJINgnPxSXdFpy2yNYOaQ6mUyiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:34:25.198673Z"},"content_sha256":"eb7ed371be1fd67f46870353a357def408f72b79e7a9cf740529847c7b70f9a1","schema_version":"1.0","event_id":"sha256:eb7ed371be1fd67f46870353a357def408f72b79e7a9cf740529847c7b70f9a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4MEUVWSUMJX64HKAXITHITNMH/bundle.json","state_url":"https://pith.science/pith/G4MEUVWSUMJX64HKAXITHITNMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4MEUVWSUMJX64HKAXITHITNMH/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":"2026-07-17T05:34:25Z","links":{"resolver":"https://pith.science/pith/G4MEUVWSUMJX64HKAXITHITNMH","bundle":"https://pith.science/pith/G4MEUVWSUMJX64HKAXITHITNMH/bundle.json","state":"https://pith.science/pith/G4MEUVWSUMJX64HKAXITHITNMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4MEUVWSUMJX64HKAXITHITNMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G4MEUVWSUMJX64HKAXITHITNMH","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":"4fe0119c1feed4fae4967bd583e3d3f16d690331e1a90af9d538059dd7d0706d","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T10:22:55Z","title_canon_sha256":"abc6802590ff2f1b441aea76e04724199d6bf9ed629b77866ec89786d4f6c0b3"},"schema_version":"1.0","source":{"id":"2211.16068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16068","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16068v2","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16068","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"G4MEUVWSUMJX","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"G4MEUVWSUMJX64HK","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"G4MEUVWS","created_at":"2026-07-05T05:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:eb7ed371be1fd67f46870353a357def408f72b79e7a9cf740529847c7b70f9a1","target":"graph","created_at":"2026-07-05T05:21:45Z","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/2211.16068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policies at the same time. Starting from first principle, in this paper, we manage to solve the non-stationarity problem by proposing bidirectional action-dependent Q-learning (ACE). Central to the development of ACE is the sequential decision-making process wherein only one agent is allowed to take action at one time. Within this process, each agent maximizes its value function given the actions taken by the preceding agen","authors_text":"Chuming Li, Jie Liu, Wanli Ouyang, Yaodong Yang, Yazhe Niu, Yinmin Zhang, Yuhong Wei, Yu Liu","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T10:22:55Z","title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16068","kind":"arxiv","version":2},"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":"sha256:865a9750bdb15b0f82b3b5db826a57874af3c2b1c9ec62a2b396406af33804dc","target":"record","created_at":"2026-07-05T05:21:45Z","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":"4fe0119c1feed4fae4967bd583e3d3f16d690331e1a90af9d538059dd7d0706d","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T10:22:55Z","title_canon_sha256":"abc6802590ff2f1b441aea76e04724199d6bf9ed629b77866ec89786d4f6c0b3"},"schema_version":"1.0","source":{"id":"2211.16068","kind":"arxiv","version":2}},"canonical_sha256":"37184a56d2a3137f70ea05d133a26d61e5143e5e64ba8c8f71617a0d11c63075","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37184a56d2a3137f70ea05d133a26d61e5143e5e64ba8c8f71617a0d11c63075","first_computed_at":"2026-07-05T05:21:45.441062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:45.441062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hnISwwOSp7NHDw3wq/H94zWEYsJFVt0uoOs6jKIzspxXG54w+IrlXGS/+WVWpTJiS3Rh/5WRmVfczukQpoiGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:45.441534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.16068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:865a9750bdb15b0f82b3b5db826a57874af3c2b1c9ec62a2b396406af33804dc","sha256:eb7ed371be1fd67f46870353a357def408f72b79e7a9cf740529847c7b70f9a1"],"state_sha256":"23608a65d74d567ec2774bcfc33136df3662ece2cfb19a720dfd8c3f671700d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1snLKTAckmhpyFf8/h3nhJcSUb8V0d5BB1/hmFdCTu9dZn5r7/U3adOQ23/tGRK3Kn19RymgEVnoAbiHE1qjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T05:34:25.200834Z","bundle_sha256":"29076b2963e0d65be47dc310efa10c1d3155aa09d0fe8f76006c3802423c85cb"}}