{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6D6BBEF57TZ4PWPLMN7LHJYUUX","short_pith_number":"pith:6D6BBEF5","schema_version":"1.0","canonical_sha256":"f0fc1090bdfcf3c7d9eb637eb3a714a5c61d772c0f3e069cd8e9e765eb3b9eb3","source":{"kind":"arxiv","id":"1907.00327","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.00327","created_at":"2026-05-17T23:41:52.147268+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00327v1","created_at":"2026-05-17T23:41:52.147268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00327","created_at":"2026-05-17T23:41:52.147268+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D6BBEF57TZ4","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D6BBEF57TZ4PWPL","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D6BBEF5","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX","json":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX.json","graph_json":"https://pith.science/api/pith-number/6D6BBEF57TZ4PWPLMN7LHJYUUX/graph.json","events_json":"https://pith.science/api/pith-number/6D6BBEF57TZ4PWPLMN7LHJYUUX/events.json","paper":"https://pith.science/paper/6D6BBEF5"},"agent_actions":{"view_html":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX","download_json":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX.json","view_paper":"https://pith.science/paper/6D6BBEF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00327&json=true","fetch_graph":"https://pith.science/api/pith-number/6D6BBEF57TZ4PWPLMN7LHJYUUX/graph.json","fetch_events":"https://pith.science/api/pith-number/6D6BBEF57TZ4PWPLMN7LHJYUUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/action/storage_attestation","attest_author":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/action/author_attestation","sign_citation":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/action/citation_signature","submit_replication":"https://pith.science/pith/6D6BBEF57TZ4PWPLMN7LHJYUUX/action/replication_record"}},"created_at":"2026-05-17T23:41:52.147268+00:00","updated_at":"2026-05-17T23:41:52.147268+00:00"}