{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6PT6PZIHJWHUQTSKSOWSEKSL3V","short_pith_number":"pith:6PT6PZIH","schema_version":"1.0","canonical_sha256":"f3e7e7e5074d8f484e4a93ad222a4bdd5220efc57e37f59df315cb1673ce4983","source":{"kind":"arxiv","id":"1912.07712","version":1},"attestation_state":"computed","paper":{"title":"Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Andrea Celli, Marco Ciccone, Nicola Gatti, Raffaele Bongo","submitted_at":"2019-12-16T21:30:04Z","abstract_excerpt":"Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries. This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for example, in Bridge, collusion in poker, and collusion in bidding. The possibility for the team members to communicate before gameplay---that is, coordinate their strategies ex ante---makes the use of behavioral strategies unsatisfactory. We introduce Soft Team Actor-Critic (STAC) as a solution to the team's coordination problem that does not require any"},"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":"1912.07712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-16T21:30:04Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"22f05afae220cced79aa4b801952899f91b185f3027c3eba5f5d17fe409b7068","abstract_canon_sha256":"f7d98218a31e39a03762a0975d00f1d9e0c8f449c342274593b0e63c4f00b358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:25.354301Z","signature_b64":"+9+MxqBWkcOJxZY17LuYYFmsPVoId2ae1eWoNtXBI6aWHwpeNSa/fn0Ml+cyNTcnlJQGVEl2TtoHGCiSEk/SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3e7e7e5074d8f484e4a93ad222a4bdd5220efc57e37f59df315cb1673ce4983","last_reissued_at":"2026-07-05T00:26:25.353819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:25.353819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Andrea Celli, Marco Ciccone, Nicola Gatti, Raffaele Bongo","submitted_at":"2019-12-16T21:30:04Z","abstract_excerpt":"Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries. This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for example, in Bridge, collusion in poker, and collusion in bidding. The possibility for the team members to communicate before gameplay---that is, coordinate their strategies ex ante---makes the use of behavioral strategies unsatisfactory. We introduce Soft Team Actor-Critic (STAC) as a solution to the team's coordination problem that does not require any"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07712","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.07712/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.07712","created_at":"2026-07-05T00:26:25.353888+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07712v1","created_at":"2026-07-05T00:26:25.353888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07712","created_at":"2026-07-05T00:26:25.353888+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PT6PZIHJWHU","created_at":"2026-07-05T00:26:25.353888+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PT6PZIHJWHUQTSK","created_at":"2026-07-05T00:26:25.353888+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PT6PZIH","created_at":"2026-07-05T00:26:25.353888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05526","citing_title":"Towards Learning Scalable Agile Dynamic Motion Planning for Robosoccer Teams with Policy Optimization","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V","json":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V.json","graph_json":"https://pith.science/api/pith-number/6PT6PZIHJWHUQTSKSOWSEKSL3V/graph.json","events_json":"https://pith.science/api/pith-number/6PT6PZIHJWHUQTSKSOWSEKSL3V/events.json","paper":"https://pith.science/paper/6PT6PZIH"},"agent_actions":{"view_html":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V","download_json":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V.json","view_paper":"https://pith.science/paper/6PT6PZIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07712&json=true","fetch_graph":"https://pith.science/api/pith-number/6PT6PZIHJWHUQTSKSOWSEKSL3V/graph.json","fetch_events":"https://pith.science/api/pith-number/6PT6PZIHJWHUQTSKSOWSEKSL3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V/action/storage_attestation","attest_author":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V/action/author_attestation","sign_citation":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V/action/citation_signature","submit_replication":"https://pith.science/pith/6PT6PZIHJWHUQTSKSOWSEKSL3V/action/replication_record"}},"created_at":"2026-07-05T00:26:25.353888+00:00","updated_at":"2026-07-05T00:26:25.353888+00:00"}