{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MO6E3JGOL5KBMJQMIZPTS5P3IR","short_pith_number":"pith:MO6E3JGO","schema_version":"1.0","canonical_sha256":"63bc4da4ce5f5416260c465f3975fb444255a10ac32be764fdfa1b593836c0e8","source":{"kind":"arxiv","id":"2301.02083","version":2},"attestation_state":"computed","paper":{"title":"Self-Motivated Multi-Agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Jiahan Cao, Lei Yuan, Shaowei Zhang, Yang Yu","submitted_at":"2023-01-05T14:42:39Z","abstract_excerpt":"In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardly accomplish the team task without coordination and they would be trapped in a local optimum where easy cooperation is accessed without enough individual exploration. Recent works mainly concentrate on agents' coordinated exploration, which brings about the exponentially grown exploration of the state space. To address this issue, we propose Self-Motivated Multi-Agent Exploration (SMMAE), which aims to achieve succes"},"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":"2301.02083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-05T14:42:39Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"21e2e89a753fadc6c1f0a1aa5a551b6c0df34133434c5afed78d3be312d4c905","abstract_canon_sha256":"7bacca5103d8bb5fa531a04d1b613ac736e96ba42c927cc23b8f3ef4bc0c805e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:53.630593Z","signature_b64":"MXcWLotB5TrJfDEs7982r4qMZtfzZxG2FiF4iRF4TU3ORQU/xI785z/fUhcW30ZiIArRdVwgavEu4gdkzfWBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63bc4da4ce5f5416260c465f3975fb444255a10ac32be764fdfa1b593836c0e8","last_reissued_at":"2026-07-05T06:54:53.630153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:53.630153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Motivated Multi-Agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Jiahan Cao, Lei Yuan, Shaowei Zhang, Yang Yu","submitted_at":"2023-01-05T14:42:39Z","abstract_excerpt":"In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardly accomplish the team task without coordination and they would be trapped in a local optimum where easy cooperation is accessed without enough individual exploration. Recent works mainly concentrate on agents' coordinated exploration, which brings about the exponentially grown exploration of the state space. To address this issue, we propose Self-Motivated Multi-Agent Exploration (SMMAE), which aims to achieve succes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02083","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/2301.02083/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":"2301.02083","created_at":"2026-07-05T06:54:53.630212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02083v2","created_at":"2026-07-05T06:54:53.630212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02083","created_at":"2026-07-05T06:54:53.630212+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO6E3JGOL5KB","created_at":"2026-07-05T06:54:53.630212+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO6E3JGOL5KBMJQM","created_at":"2026-07-05T06:54:53.630212+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO6E3JGO","created_at":"2026-07-05T06:54:53.630212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR","json":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR.json","graph_json":"https://pith.science/api/pith-number/MO6E3JGOL5KBMJQMIZPTS5P3IR/graph.json","events_json":"https://pith.science/api/pith-number/MO6E3JGOL5KBMJQMIZPTS5P3IR/events.json","paper":"https://pith.science/paper/MO6E3JGO"},"agent_actions":{"view_html":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR","download_json":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR.json","view_paper":"https://pith.science/paper/MO6E3JGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02083&json=true","fetch_graph":"https://pith.science/api/pith-number/MO6E3JGOL5KBMJQMIZPTS5P3IR/graph.json","fetch_events":"https://pith.science/api/pith-number/MO6E3JGOL5KBMJQMIZPTS5P3IR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR/action/storage_attestation","attest_author":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR/action/author_attestation","sign_citation":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR/action/citation_signature","submit_replication":"https://pith.science/pith/MO6E3JGOL5KBMJQMIZPTS5P3IR/action/replication_record"}},"created_at":"2026-07-05T06:54:53.630212+00:00","updated_at":"2026-07-05T06:54:53.630212+00:00"}