{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DDBXYOYRWGQX53J4LXGRKT5CGQ","short_pith_number":"pith:DDBXYOYR","canonical_record":{"source":{"id":"1810.09206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2018-10-22T12:24:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12ad6844b62fc96580442ee21a80da7ea1f25a3cf6ed043c201e2af9d7da2519","abstract_canon_sha256":"6f635392d302930822b636a6ec90c2a80ff83f68c8824dbc6de11009c6183cd8"},"schema_version":"1.0"},"canonical_sha256":"18c37c3b11b1a17eed3c5dcd154fa2342995ac1c53aff09b19509443902c07f5","source":{"kind":"arxiv","id":"1810.09206","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09206","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09206v1","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09206","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"DDBXYOYRWGQX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DDBXYOYRWGQX53J4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DDBXYOYR","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DDBXYOYRWGQX53J4LXGRKT5CGQ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.09206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2018-10-22T12:24:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12ad6844b62fc96580442ee21a80da7ea1f25a3cf6ed043c201e2af9d7da2519","abstract_canon_sha256":"6f635392d302930822b636a6ec90c2a80ff83f68c8824dbc6de11009c6183cd8"},"schema_version":"1.0"},"canonical_sha256":"18c37c3b11b1a17eed3c5dcd154fa2342995ac1c53aff09b19509443902c07f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:40.794753Z","signature_b64":"8Psj4Z1Fgty+BRkeBjVWy5bx2w3ssOxPn9O3EhB3Yn2tUNfnFVxd2zmm1VRCmVCum5RvwR/NS8fbLk/ZhYPhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18c37c3b11b1a17eed3c5dcd154fa2342995ac1c53aff09b19509443902c07f5","last_reissued_at":"2026-05-18T00:02:40.794229Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:40.794229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.09206","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":"2026-05-18T00:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9z9H08FMYZXJOjryrmILF6hdhARKapB+zUmzSOK1wKFKKMjQO7I+g4v7UyBLJQ8cCDebpNqtDNhJPYaOhoGZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T02:15:31.924402Z"},"content_sha256":"8068480df8302a036d804952caaec6577a37bfcb8adf9b608e346114f08e7cf6","schema_version":"1.0","event_id":"sha256:8068480df8302a036d804952caaec6577a37bfcb8adf9b608e346114f08e7cf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DDBXYOYRWGQX53J4LXGRKT5CGQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Actor-Critic with Generative Cooperative Policy Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Hayong Shin, Heechang Ryu, Jinkyoo Park","submitted_at":"2018-10-22T12:24:11Z","abstract_excerpt":"We propose an efficient multi-agent reinforcement learning approach to derive equilibrium strategies for multi-agents who are participating in a Markov game. Mainly, we are focused on obtaining decentralized policies for agents to maximize the performance of a collaborative task by all the agents, which is similar to solving a decentralized Markov decision process. We propose to use two different policy networks: (1) decentralized greedy policy network used to generate greedy action during training and execution period and (2) generative cooperative policy network (GCPN) used to generate actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09206","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":"2026-05-18T00:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"viReBYFql2zH6WTA1JIL0/lslY1NgzTCeOuPDGwQjIAbw0aYn6SbggalDgKjUtfiu4cpyO+2nea58+h7NSFIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T02:15:31.925065Z"},"content_sha256":"883e487a3955c8cf0af4e8613718f317a9615696fcfcd904d3cd9b4f0a07600d","schema_version":"1.0","event_id":"sha256:883e487a3955c8cf0af4e8613718f317a9615696fcfcd904d3cd9b4f0a07600d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/bundle.json","state_url":"https://pith.science/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/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":"2026-05-19T02:15:31Z","links":{"resolver":"https://pith.science/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ","bundle":"https://pith.science/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/bundle.json","state":"https://pith.science/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDBXYOYRWGQX53J4LXGRKT5CGQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DDBXYOYRWGQX53J4LXGRKT5CGQ","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":"6f635392d302930822b636a6ec90c2a80ff83f68c8824dbc6de11009c6183cd8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2018-10-22T12:24:11Z","title_canon_sha256":"12ad6844b62fc96580442ee21a80da7ea1f25a3cf6ed043c201e2af9d7da2519"},"schema_version":"1.0","source":{"id":"1810.09206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09206","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09206v1","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09206","created_at":"2026-05-18T00:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"DDBXYOYRWGQX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DDBXYOYRWGQX53J4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DDBXYOYR","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:883e487a3955c8cf0af4e8613718f317a9615696fcfcd904d3cd9b4f0a07600d","target":"graph","created_at":"2026-05-18T00:02:40Z","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 propose an efficient multi-agent reinforcement learning approach to derive equilibrium strategies for multi-agents who are participating in a Markov game. Mainly, we are focused on obtaining decentralized policies for agents to maximize the performance of a collaborative task by all the agents, which is similar to solving a decentralized Markov decision process. We propose to use two different policy networks: (1) decentralized greedy policy network used to generate greedy action during training and execution period and (2) generative cooperative policy network (GCPN) used to generate actio","authors_text":"Hayong Shin, Heechang Ryu, Jinkyoo Park","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2018-10-22T12:24:11Z","title":"Multi-Agent Actor-Critic with Generative Cooperative Policy Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09206","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":"sha256:8068480df8302a036d804952caaec6577a37bfcb8adf9b608e346114f08e7cf6","target":"record","created_at":"2026-05-18T00:02:40Z","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":"6f635392d302930822b636a6ec90c2a80ff83f68c8824dbc6de11009c6183cd8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2018-10-22T12:24:11Z","title_canon_sha256":"12ad6844b62fc96580442ee21a80da7ea1f25a3cf6ed043c201e2af9d7da2519"},"schema_version":"1.0","source":{"id":"1810.09206","kind":"arxiv","version":1}},"canonical_sha256":"18c37c3b11b1a17eed3c5dcd154fa2342995ac1c53aff09b19509443902c07f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c37c3b11b1a17eed3c5dcd154fa2342995ac1c53aff09b19509443902c07f5","first_computed_at":"2026-05-18T00:02:40.794229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:40.794229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Psj4Z1Fgty+BRkeBjVWy5bx2w3ssOxPn9O3EhB3Yn2tUNfnFVxd2zmm1VRCmVCum5RvwR/NS8fbLk/ZhYPhAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:40.794753Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.09206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8068480df8302a036d804952caaec6577a37bfcb8adf9b608e346114f08e7cf6","sha256:883e487a3955c8cf0af4e8613718f317a9615696fcfcd904d3cd9b4f0a07600d"],"state_sha256":"6024abe59d4b6b218129e08e5cc543ab74b1df862c6468b3ec26314cf3dd064f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WS1PP62WOVAecw8Lrc6/lD1hm24d6wjxN6wdGPcNZHNqQ3tf3dtQmi7zDLgCRaaoLEfb8QHWGGk/1hd36yGOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T02:15:31.927064Z","bundle_sha256":"6862e585140e753bfe3dffea0edca19db2039e5fe62cdccf31af130b5401667b"}}