{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQ3L42MVOROMYHBVODWWUSTDP7","short_pith_number":"pith:UQ3L42MV","schema_version":"1.0","canonical_sha256":"a436be6995745ccc1c3570ed6a4a637fd884ad307135e7cfcb4f8a7f468be916","source":{"kind":"arxiv","id":"2403.08936","version":3},"attestation_state":"computed","paper":{"title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Alec Koppel, Amrit Bedi, Carl Busart, Dinesh Manocha, Manav Mishra, Peihong Yu, Pratap Tokekar, Priya Narayan","submitted_at":"2024-03-13T20:11:20Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space. While demonstration-guided learning has proven beneficial in single-agent settings, its direct applicability to MARL is hindered by the practical difficulty of obtaining joint expert demonstrations. In this work, we introduce a novel concept of personalized expert demonstrations, tailored for each individual agent or, more broadly, each individual type of agent within a heterogeneous team. These demonstrations solely perta"},"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":"2403.08936","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-03-13T20:11:20Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e1e63d263ff96d8f292afbc7a7e1e28256596ec593262f426c3f86b601eae17b","abstract_canon_sha256":"982f0811b9687e8dd1c667222dc697d16f6f5ee7e93e2cc45f60fc93f95ee6d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:50.280033Z","signature_b64":"K1NqPM90h7gBIh2kHs6VEFe5dyL1dUKQnA18esbZzn/BuEkN4hrt5SmeCyNbZgiSPx+2Kwda/oCcDUsypHQECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a436be6995745ccc1c3570ed6a4a637fd884ad307135e7cfcb4f8a7f468be916","last_reissued_at":"2026-07-05T09:56:50.279476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:50.279476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Alec Koppel, Amrit Bedi, Carl Busart, Dinesh Manocha, Manav Mishra, Peihong Yu, Pratap Tokekar, Priya Narayan","submitted_at":"2024-03-13T20:11:20Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space. While demonstration-guided learning has proven beneficial in single-agent settings, its direct applicability to MARL is hindered by the practical difficulty of obtaining joint expert demonstrations. In this work, we introduce a novel concept of personalized expert demonstrations, tailored for each individual agent or, more broadly, each individual type of agent within a heterogeneous team. These demonstrations solely perta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08936","kind":"arxiv","version":3},"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/2403.08936/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":"2403.08936","created_at":"2026-07-05T09:56:50.279550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08936v3","created_at":"2026-07-05T09:56:50.279550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08936","created_at":"2026-07-05T09:56:50.279550+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQ3L42MVOROM","created_at":"2026-07-05T09:56:50.279550+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQ3L42MVOROMYHBV","created_at":"2026-07-05T09:56:50.279550+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQ3L42MV","created_at":"2026-07-05T09:56:50.279550+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/UQ3L42MVOROMYHBVODWWUSTDP7","json":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7.json","graph_json":"https://pith.science/api/pith-number/UQ3L42MVOROMYHBVODWWUSTDP7/graph.json","events_json":"https://pith.science/api/pith-number/UQ3L42MVOROMYHBVODWWUSTDP7/events.json","paper":"https://pith.science/paper/UQ3L42MV"},"agent_actions":{"view_html":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7","download_json":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7.json","view_paper":"https://pith.science/paper/UQ3L42MV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08936&json=true","fetch_graph":"https://pith.science/api/pith-number/UQ3L42MVOROMYHBVODWWUSTDP7/graph.json","fetch_events":"https://pith.science/api/pith-number/UQ3L42MVOROMYHBVODWWUSTDP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7/action/storage_attestation","attest_author":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7/action/author_attestation","sign_citation":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7/action/citation_signature","submit_replication":"https://pith.science/pith/UQ3L42MVOROMYHBVODWWUSTDP7/action/replication_record"}},"created_at":"2026-07-05T09:56:50.279550+00:00","updated_at":"2026-07-05T09:56:50.279550+00:00"}