{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SIZ4QYX54AOZZMMJELRFCUGHIE","short_pith_number":"pith:SIZ4QYX5","schema_version":"1.0","canonical_sha256":"9233c862fde01d9cb18922e25150c7412f3e676738a9eff457701a5c0109b6ba","source":{"kind":"arxiv","id":"2210.06274","version":2},"attestation_state":"computed","paper":{"title":"Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Sardinha, Ana Paiva, Diogo S. Carvalho, Francisco S. Melo, Miguel Vasco, Pedro A. Santos, Pedro P. Santos","submitted_at":"2022-10-12T14:58:32Z","abstract_excerpt":"We introduce hybrid execution in multi-agent reinforcement learning (MARL), a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents. Under hybrid execution, the communication level can range from a setting in which no communication is allowed between agents (fully decentralized), to a setting featuring full communication (fully centralized), but the agents do not know beforehand which communication level they will encounter at execution time. To formalize our "},"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":"2210.06274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T14:58:32Z","cross_cats_sorted":[],"title_canon_sha256":"0411b2b39a726c34afa53495c1fa29372a32cdcc8f41322ac846ef7739b9266f","abstract_canon_sha256":"3a0cb573dbdd0801f618d3192dde7bdb2861ce3b9f5a4b0f7d5e048a4595d272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:26.597098Z","signature_b64":"pJmLkXQXrUfWfgJIuRMEpbfbYha//Wug3ZTuCZjm+zJCAy+AiLlxUG2S+1hpNNuflzgToV5ExrTEasUaWPC0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9233c862fde01d9cb18922e25150c7412f3e676738a9eff457701a5c0109b6ba","last_reissued_at":"2026-07-05T06:17:26.596626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:26.596626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Sardinha, Ana Paiva, Diogo S. Carvalho, Francisco S. Melo, Miguel Vasco, Pedro A. Santos, Pedro P. Santos","submitted_at":"2022-10-12T14:58:32Z","abstract_excerpt":"We introduce hybrid execution in multi-agent reinforcement learning (MARL), a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents. Under hybrid execution, the communication level can range from a setting in which no communication is allowed between agents (fully decentralized), to a setting featuring full communication (fully centralized), but the agents do not know beforehand which communication level they will encounter at execution time. To formalize our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06274","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/2210.06274/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":"2210.06274","created_at":"2026-07-05T06:17:26.596698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06274v2","created_at":"2026-07-05T06:17:26.596698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06274","created_at":"2026-07-05T06:17:26.596698+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIZ4QYX54AOZ","created_at":"2026-07-05T06:17:26.596698+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIZ4QYX54AOZZMMJ","created_at":"2026-07-05T06:17:26.596698+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIZ4QYX5","created_at":"2026-07-05T06:17:26.596698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15756","citing_title":"RecBayes: Recurrent Bayesian Ad Hoc Teamwork in Large Partially Observable Domains","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE","json":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE.json","graph_json":"https://pith.science/api/pith-number/SIZ4QYX54AOZZMMJELRFCUGHIE/graph.json","events_json":"https://pith.science/api/pith-number/SIZ4QYX54AOZZMMJELRFCUGHIE/events.json","paper":"https://pith.science/paper/SIZ4QYX5"},"agent_actions":{"view_html":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE","download_json":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE.json","view_paper":"https://pith.science/paper/SIZ4QYX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06274&json=true","fetch_graph":"https://pith.science/api/pith-number/SIZ4QYX54AOZZMMJELRFCUGHIE/graph.json","fetch_events":"https://pith.science/api/pith-number/SIZ4QYX54AOZZMMJELRFCUGHIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE/action/storage_attestation","attest_author":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE/action/author_attestation","sign_citation":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE/action/citation_signature","submit_replication":"https://pith.science/pith/SIZ4QYX54AOZZMMJELRFCUGHIE/action/replication_record"}},"created_at":"2026-07-05T06:17:26.596698+00:00","updated_at":"2026-07-05T06:17:26.596698+00:00"}