{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MJQ5N3T64MI7XSGH2ILATZMM7N","short_pith_number":"pith:MJQ5N3T6","schema_version":"1.0","canonical_sha256":"6261d6ee7ee311fbc8c7d21609e58cfb7f83d66f4f3d7e1100e2012a54385a7c","source":{"kind":"arxiv","id":"2409.17348","version":2},"attestation_state":"computed","paper":{"title":"Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Behdad Chalaki, Charles Michael Lewis, Ehsan Moradi-Pari, Hossein Nourkhiz Mahjoub, Huao Li, Katia P Sycara, Kwonjoon Lee, Vaishnav Tadiparthi","submitted_at":"2024-09-25T20:49:41Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable to humans or other agents not co-trained together, limiting its applicability in ad-hoc teamwork scenarios. In this work, we propose a novel computational pipeline that aligns the communication space between MARL agents with an embedding space of human natural language by grounding agent communications on synthetic data generated by embodied Large Language M"},"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":"2409.17348","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MA","submitted_at":"2024-09-25T20:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"d5bf6a0fe91579c1b84d2f73d5b10b20d34ec07b92b6892e9d9e8c0dd319d894","abstract_canon_sha256":"77045c1c1430a67042b7c34f95947c652b75976c37fe9473f324200c19485988"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:58.741487Z","signature_b64":"n05pS2jX7AsNNuhl5Ussht/cPfhwsWHuriKgr7cRLrNw1YxA2MLV2rc6Fc0eUNYmBfOCgkdDJaYZiklxSA/AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6261d6ee7ee311fbc8c7d21609e58cfb7f83d66f4f3d7e1100e2012a54385a7c","last_reissued_at":"2026-07-05T09:39:58.741042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:58.741042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Behdad Chalaki, Charles Michael Lewis, Ehsan Moradi-Pari, Hossein Nourkhiz Mahjoub, Huao Li, Katia P Sycara, Kwonjoon Lee, Vaishnav Tadiparthi","submitted_at":"2024-09-25T20:49:41Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable to humans or other agents not co-trained together, limiting its applicability in ad-hoc teamwork scenarios. In this work, we propose a novel computational pipeline that aligns the communication space between MARL agents with an embedding space of human natural language by grounding agent communications on synthetic data generated by embodied Large Language M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17348","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/2409.17348/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":"2409.17348","created_at":"2026-07-05T09:39:58.741099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17348v2","created_at":"2026-07-05T09:39:58.741099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17348","created_at":"2026-07-05T09:39:58.741099+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJQ5N3T64MI7","created_at":"2026-07-05T09:39:58.741099+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJQ5N3T64MI7XSGH","created_at":"2026-07-05T09:39:58.741099+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJQ5N3T6","created_at":"2026-07-05T09:39:58.741099+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/MJQ5N3T64MI7XSGH2ILATZMM7N","json":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N.json","graph_json":"https://pith.science/api/pith-number/MJQ5N3T64MI7XSGH2ILATZMM7N/graph.json","events_json":"https://pith.science/api/pith-number/MJQ5N3T64MI7XSGH2ILATZMM7N/events.json","paper":"https://pith.science/paper/MJQ5N3T6"},"agent_actions":{"view_html":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N","download_json":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N.json","view_paper":"https://pith.science/paper/MJQ5N3T6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17348&json=true","fetch_graph":"https://pith.science/api/pith-number/MJQ5N3T64MI7XSGH2ILATZMM7N/graph.json","fetch_events":"https://pith.science/api/pith-number/MJQ5N3T64MI7XSGH2ILATZMM7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N/action/storage_attestation","attest_author":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N/action/author_attestation","sign_citation":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N/action/citation_signature","submit_replication":"https://pith.science/pith/MJQ5N3T64MI7XSGH2ILATZMM7N/action/replication_record"}},"created_at":"2026-07-05T09:39:58.741099+00:00","updated_at":"2026-07-05T09:39:58.741099+00:00"}