{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NSQFEJ5HFLR5BPCU3KW3U6VMM6","short_pith_number":"pith:NSQFEJ5H","schema_version":"1.0","canonical_sha256":"6ca05227a72ae3d0bc54daadba7aac67aa89a5d09208db3496c29e4fe3fca780","source":{"kind":"arxiv","id":"2107.11444","version":1},"attestation_state":"computed","paper":{"title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander G. Schwing, Iou-Jen Liu, Raymond A. Yeh, Unnat Jain","submitted_at":"2021-07-23T20:06:32Z","abstract_excerpt":"Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE):"},"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":"2107.11444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-23T20:06:32Z","cross_cats_sorted":[],"title_canon_sha256":"a09a2644cb601afdba9b1a1e3eab95b987099e412691b6b128e65cbbdd0f579c","abstract_canon_sha256":"3bf56d3487b9f15ab59f4a4744072fdd8549720e11f32a458abaca4cf33335db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:19.392902Z","signature_b64":"rSk337fov7BkXj4+Qg4TThQsq16jmaTr11USfKCjir29tPq6XFF3Su4Bd/T7kcVcSLoaj8Yakw7Xuv7FrtqYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ca05227a72ae3d0bc54daadba7aac67aa89a5d09208db3496c29e4fe3fca780","last_reissued_at":"2026-07-05T03:00:19.392503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:19.392503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander G. Schwing, Iou-Jen Liu, Raymond A. Yeh, Unnat Jain","submitted_at":"2021-07-23T20:06:32Z","abstract_excerpt":"Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE):"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11444","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/2107.11444/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":"2107.11444","created_at":"2026-07-05T03:00:19.392562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11444v1","created_at":"2026-07-05T03:00:19.392562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11444","created_at":"2026-07-05T03:00:19.392562+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSQFEJ5HFLR5","created_at":"2026-07-05T03:00:19.392562+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSQFEJ5HFLR5BPCU","created_at":"2026-07-05T03:00:19.392562+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSQFEJ5H","created_at":"2026-07-05T03:00:19.392562+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/NSQFEJ5HFLR5BPCU3KW3U6VMM6","json":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6.json","graph_json":"https://pith.science/api/pith-number/NSQFEJ5HFLR5BPCU3KW3U6VMM6/graph.json","events_json":"https://pith.science/api/pith-number/NSQFEJ5HFLR5BPCU3KW3U6VMM6/events.json","paper":"https://pith.science/paper/NSQFEJ5H"},"agent_actions":{"view_html":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6","download_json":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6.json","view_paper":"https://pith.science/paper/NSQFEJ5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11444&json=true","fetch_graph":"https://pith.science/api/pith-number/NSQFEJ5HFLR5BPCU3KW3U6VMM6/graph.json","fetch_events":"https://pith.science/api/pith-number/NSQFEJ5HFLR5BPCU3KW3U6VMM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6/action/storage_attestation","attest_author":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6/action/author_attestation","sign_citation":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6/action/citation_signature","submit_replication":"https://pith.science/pith/NSQFEJ5HFLR5BPCU3KW3U6VMM6/action/replication_record"}},"created_at":"2026-07-05T03:00:19.392562+00:00","updated_at":"2026-07-05T03:00:19.392562+00:00"}