{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6D6BBEF57TZ4PWPLMN7LHJYUUX","short_pith_number":"pith:6D6BBEF5","canonical_record":{"source":{"id":"1907.00327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-06-30T06:12:48Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e84b1abc422078060d331da245f75fd2aca4dad2c085e6c9cd05ac1ad2ff50a0","abstract_canon_sha256":"0bcc9ecaf9acecf07ad1b7cbdfefa95df318e7dc4b9de18e21527ce5329cfcf6"},"schema_version":"1.0"},"canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","source":{"kind":"arxiv","id":"1907.00327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00327","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00327v1","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00327","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"6D6BBEF57TZ4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6D6BBEF57TZ4PWPL","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6D6BBEF5","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6D6BBEF57TZ4PWPLMN7LHJYUUX","target":"record","payload":{"canonical_record":{"source":{"id":"1907.00327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-06-30T06:12:48Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e84b1abc422078060d331da245f75fd2aca4dad2c085e6c9cd05ac1ad2ff50a0","abstract_canon_sha256":"0bcc9ecaf9acecf07ad1b7cbdfefa95df318e7dc4b9de18e21527ce5329cfcf6"},"schema_version":"1.0"},"canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:52.147902Z","signature_b64":"+gJTKHOqqq/gwxz6Klh7Mv3/7BvZ3K7qVU9EpvUxcsrSGnwBAFRB8fntLQRAenUPc/cL408HHKV4+b2UPpZKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","last_reissued_at":"2026-05-17T23:41:52.147142Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:52.147142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.00327","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":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqTn+f7Hr8oM8V+Svj7bsgUvrjFv5uCYPqGb+bQqq2s87ZodbHUBrVz3vnYV0OOacyPH7dz6HSPueq6sCbYACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T12:19:16.568081Z"},"content_sha256":"739cd6c81e8aa4bd553c00dff4faa1c0a17fa723d1e8e093d573f2a1ca2875e2","schema_version":"1.0","event_id":"sha256:739cd6c81e8aa4bd553c00dff4faa1c0a17fa723d1e8e093d573f2a1ca2875e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6D6BBEF57TZ4PWPLMN7LHJYUUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collaboration of AI Agents via Cooperative Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.MA","authors_text":"Govardana Sachithanandam Ramachandran, Justin Dieter, Niranjan Balachandar","submitted_at":"2019-06-30T06:12:48Z","abstract_excerpt":"There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train agents to collaborate with teammates in grid soccer. We train and evaluate our multi-agent methods against a team operating with a smart hand-coded policy. As a baseline, we train agents concurrently and independently, with no communication. Our collaborative protocols were parameter sharing, coordinated learning with communication, and counterfactual policy gradients. Against th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00327","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":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wq38BlHF20J4Fm1mmvXBx/oG2iKAPS8RFeONcxjy6hOlFqnxrUGGqKOXS/KsAOGKyo1wd19wBGWGJcM5fLdyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T12:19:16.568436Z"},"content_sha256":"ec552ef5d956f2d5746c1c833a4c6d4637a2f686c8885fb21ad9939940a653cc","schema_version":"1.0","event_id":"sha256:ec552ef5d956f2d5746c1c833a4c6d4637a2f686c8885fb21ad9939940a653cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/bundle.json","state_url":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/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":"2026-06-28T12:19:16Z","links":{"resolver":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX","bundle":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/bundle.json","state":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6D6BBEF57TZ4PWPLMN7LHJYUUX","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":"0bcc9ecaf9acecf07ad1b7cbdfefa95df318e7dc4b9de18e21527ce5329cfcf6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-06-30T06:12:48Z","title_canon_sha256":"e84b1abc422078060d331da245f75fd2aca4dad2c085e6c9cd05ac1ad2ff50a0"},"schema_version":"1.0","source":{"id":"1907.00327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00327","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00327v1","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00327","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"6D6BBEF57TZ4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6D6BBEF57TZ4PWPL","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6D6BBEF5","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:ec552ef5d956f2d5746c1c833a4c6d4637a2f686c8885fb21ad9939940a653cc","target":"graph","created_at":"2026-05-17T23:41:52Z","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":"There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train agents to collaborate with teammates in grid soccer. We train and evaluate our multi-agent methods against a team operating with a smart hand-coded policy. As a baseline, we train agents concurrently and independently, with no communication. Our collaborative protocols were parameter sharing, coordinated learning with communication, and counterfactual policy gradients. Against th","authors_text":"Govardana Sachithanandam Ramachandran, Justin Dieter, Niranjan Balachandar","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-06-30T06:12:48Z","title":"Collaboration of AI Agents via Cooperative Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00327","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":"sha256:739cd6c81e8aa4bd553c00dff4faa1c0a17fa723d1e8e093d573f2a1ca2875e2","target":"record","created_at":"2026-05-17T23:41:52Z","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":"0bcc9ecaf9acecf07ad1b7cbdfefa95df318e7dc4b9de18e21527ce5329cfcf6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-06-30T06:12:48Z","title_canon_sha256":"e84b1abc422078060d331da245f75fd2aca4dad2c085e6c9cd05ac1ad2ff50a0"},"schema_version":"1.0","source":{"id":"1907.00327","kind":"arxiv","version":1}},"canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","first_computed_at":"2026-05-17T23:41:52.147142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:52.147142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+gJTKHOqqq/gwxz6Klh7Mv3/7BvZ3K7qVU9EpvUxcsrSGnwBAFRB8fntLQRAenUPc/cL408HHKV4+b2UPpZKAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:52.147902Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:739cd6c81e8aa4bd553c00dff4faa1c0a17fa723d1e8e093d573f2a1ca2875e2","sha256:ec552ef5d956f2d5746c1c833a4c6d4637a2f686c8885fb21ad9939940a653cc"],"state_sha256":"694a0d71fb5757de43bc5b6c7292530af1081119a6508ba435aab5d7c20403db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZsUJoGJgClz2+dVIgPzgjnFkN2sy3GlHyrnyKAnMXxLWk7TMExFSGDSTHkH5Z7l+Q31KNKgG3kcVCF3kxmwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T12:19:16.570300Z","bundle_sha256":"f0ebd1a4d42b942a7a075f8ae3abd4d9f0edae6e35f1067fdf9902520f20151e"}}