{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L43NKZIAMPCKPXFGSFT6QLQFPI","short_pith_number":"pith:L43NKZIA","schema_version":"1.0","canonical_sha256":"5f36d5650063c4a7dca69167e82e057a14ad704eab2310b961e0e96a51b018ff","source":{"kind":"arxiv","id":"2401.11378","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dong Jiang, Guangliang Li, Tianhao Chen, Zheng Fang, Zheng Zhang","submitted_at":"2024-01-21T03:01:00Z","abstract_excerpt":"Multiple autonomous underwater vehicles (multi-AUV) can cooperatively accomplish tasks that a single AUV cannot complete. Recently, multi-agent reinforcement learning has been introduced to control of multi-AUV. However, designing efficient reward functions for various tasks of multi-AUV control is difficult or even impractical. Multi-agent generative adversarial imitation learning (MAGAIL) allows multi-AUV to learn from expert demonstration instead of pre-defined reward functions, but suffers from the deficiency of requiring optimal demonstrations and not surpassing provided expert demonstrat"},"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":"2401.11378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T03:01:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c629745e78eb634522ef72c70d5bbe89affb89508e34919364e018c1db73a55b","abstract_canon_sha256":"d1cfd3cc3e638c5e3aa8515e8474876ad04cfca4a69262871756cd3ee5120f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:49.881880Z","signature_b64":"5V7BVgz8kOHPCwW76D/PU2QNepg2f1Wm//zVDA6n2K2sKgTiuogjjtNo+DL6JDuAdMCJrCX6ieRMDxO5q8aqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f36d5650063c4a7dca69167e82e057a14ad704eab2310b961e0e96a51b018ff","last_reissued_at":"2026-07-05T07:35:49.881423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:49.881423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dong Jiang, Guangliang Li, Tianhao Chen, Zheng Fang, Zheng Zhang","submitted_at":"2024-01-21T03:01:00Z","abstract_excerpt":"Multiple autonomous underwater vehicles (multi-AUV) can cooperatively accomplish tasks that a single AUV cannot complete. Recently, multi-agent reinforcement learning has been introduced to control of multi-AUV. However, designing efficient reward functions for various tasks of multi-AUV control is difficult or even impractical. Multi-agent generative adversarial imitation learning (MAGAIL) allows multi-AUV to learn from expert demonstration instead of pre-defined reward functions, but suffers from the deficiency of requiring optimal demonstrations and not surpassing provided expert demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11378","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/2401.11378/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":"2401.11378","created_at":"2026-07-05T07:35:49.881477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11378v1","created_at":"2026-07-05T07:35:49.881477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11378","created_at":"2026-07-05T07:35:49.881477+00:00"},{"alias_kind":"pith_short_12","alias_value":"L43NKZIAMPCK","created_at":"2026-07-05T07:35:49.881477+00:00"},{"alias_kind":"pith_short_16","alias_value":"L43NKZIAMPCKPXFG","created_at":"2026-07-05T07:35:49.881477+00:00"},{"alias_kind":"pith_short_8","alias_value":"L43NKZIA","created_at":"2026-07-05T07:35:49.881477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06113","citing_title":"Towards Bio-inspired Heuristically Accelerated Reinforcement Learning for Adaptive Underwater Multi-Agents Behaviour","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI","json":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI.json","graph_json":"https://pith.science/api/pith-number/L43NKZIAMPCKPXFGSFT6QLQFPI/graph.json","events_json":"https://pith.science/api/pith-number/L43NKZIAMPCKPXFGSFT6QLQFPI/events.json","paper":"https://pith.science/paper/L43NKZIA"},"agent_actions":{"view_html":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI","download_json":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI.json","view_paper":"https://pith.science/paper/L43NKZIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11378&json=true","fetch_graph":"https://pith.science/api/pith-number/L43NKZIAMPCKPXFGSFT6QLQFPI/graph.json","fetch_events":"https://pith.science/api/pith-number/L43NKZIAMPCKPXFGSFT6QLQFPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI/action/storage_attestation","attest_author":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI/action/author_attestation","sign_citation":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI/action/citation_signature","submit_replication":"https://pith.science/pith/L43NKZIAMPCKPXFGSFT6QLQFPI/action/replication_record"}},"created_at":"2026-07-05T07:35:49.881477+00:00","updated_at":"2026-07-05T07:35:49.881477+00:00"}