{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ULWF5RXVSW4IEG4SKIQDDH2BCA","short_pith_number":"pith:ULWF5RXV","schema_version":"1.0","canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","source":{"kind":"arxiv","id":"2501.12061","version":1},"attestation_state":"computed","paper":{"title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Pallab Dasgupta, Somnath Hazra, Soumyajit Dey","submitted_at":"2025-01-21T11:31:01Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy learning. While Distributional Reinforcement Learning has been successfully applied in single-agent settings to address risk and uncertainty, its application in MARL is substantially limited. In this work, we propose a novel approach that integrates distributional learning with a safety-focused loss function to improve convergence in cooperative MARL tasks. "},"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":"2501.12061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"539b3aa611e57bcc2000b3355dbc445397ecc3f20b2ba0739f9a8bab98cd2ed3","abstract_canon_sha256":"56761678b7a23fd0db73329ff988ce5f9692880cb4975485cdc0b331511bde0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:31.266532Z","signature_b64":"4kqCbkRNpWJkpEwmMiz5RX2Vhlmvw12rspT+me+p2w5Wg6ojy6grlqMLI2MgyFQKPAQKqiM8wi5Vq3+dC8/NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","last_reissued_at":"2026-07-05T10:03:31.266139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:31.266139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Pallab Dasgupta, Somnath Hazra, Soumyajit Dey","submitted_at":"2025-01-21T11:31:01Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy learning. While Distributional Reinforcement Learning has been successfully applied in single-agent settings to address risk and uncertainty, its application in MARL is substantially limited. In this work, we propose a novel approach that integrates distributional learning with a safety-focused loss function to improve convergence in cooperative MARL tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12061","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/2501.12061/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":"2501.12061","created_at":"2026-07-05T10:03:31.266195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12061v1","created_at":"2026-07-05T10:03:31.266195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12061","created_at":"2026-07-05T10:03:31.266195+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULWF5RXVSW4I","created_at":"2026-07-05T10:03:31.266195+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULWF5RXVSW4IEG4S","created_at":"2026-07-05T10:03:31.266195+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULWF5RXV","created_at":"2026-07-05T10:03:31.266195+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/ULWF5RXVSW4IEG4SKIQDDH2BCA","json":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA.json","graph_json":"https://pith.science/api/pith-number/ULWF5RXVSW4IEG4SKIQDDH2BCA/graph.json","events_json":"https://pith.science/api/pith-number/ULWF5RXVSW4IEG4SKIQDDH2BCA/events.json","paper":"https://pith.science/paper/ULWF5RXV"},"agent_actions":{"view_html":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA","download_json":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA.json","view_paper":"https://pith.science/paper/ULWF5RXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12061&json=true","fetch_graph":"https://pith.science/api/pith-number/ULWF5RXVSW4IEG4SKIQDDH2BCA/graph.json","fetch_events":"https://pith.science/api/pith-number/ULWF5RXVSW4IEG4SKIQDDH2BCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/action/storage_attestation","attest_author":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/action/author_attestation","sign_citation":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/action/citation_signature","submit_replication":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/action/replication_record"}},"created_at":"2026-07-05T10:03:31.266195+00:00","updated_at":"2026-07-05T10:03:31.266195+00:00"}