{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GOMHCDMSONLZTYP7URERIXS6SX","short_pith_number":"pith:GOMHCDMS","schema_version":"1.0","canonical_sha256":"3398710d92735799e1ffa449145e5e95ff143ed64f61b460f7ebc430050449e4","source":{"kind":"arxiv","id":"2405.18110","version":1},"attestation_state":"computed","paper":{"title":"Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Shibo Chen, Xinran Li, Zifan Liu","submitted_at":"2024-05-28T12:18:19Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent's contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centr"},"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":"2405.18110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:18:19Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"330d3e37afbc6e36534e4a7febafe3e2867055c4590c5f912ab260844c5128dc","abstract_canon_sha256":"b02b4761b266e8fbbb659b4a32ac641a76f8d9baa7ac6d5b0eca07637e412f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:15.779423Z","signature_b64":"v8TcF2lTEhS9enFvHc351izi51hcDHN2Qm7676Xjky9p6QC7zjgK02I9mg2TeJv+FcXBl2MXOsJhfds06vsFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3398710d92735799e1ffa449145e5e95ff143ed64f61b460f7ebc430050449e4","last_reissued_at":"2026-07-05T08:24:15.779063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:15.779063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Shibo Chen, Xinran Li, Zifan Liu","submitted_at":"2024-05-28T12:18:19Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent's contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18110","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/2405.18110/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":"2405.18110","created_at":"2026-07-05T08:24:15.779119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18110v1","created_at":"2026-07-05T08:24:15.779119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18110","created_at":"2026-07-05T08:24:15.779119+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOMHCDMSONLZ","created_at":"2026-07-05T08:24:15.779119+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOMHCDMSONLZTYP7","created_at":"2026-07-05T08:24:15.779119+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOMHCDMS","created_at":"2026-07-05T08:24:15.779119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00055","citing_title":"TinyMA-IEI-PPO: Exploration Incentive-Driven Multi-Agent DRL with Self-Adaptive Pruning for Vehicular Embodied AI Agent Twins Migration","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX","json":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX.json","graph_json":"https://pith.science/api/pith-number/GOMHCDMSONLZTYP7URERIXS6SX/graph.json","events_json":"https://pith.science/api/pith-number/GOMHCDMSONLZTYP7URERIXS6SX/events.json","paper":"https://pith.science/paper/GOMHCDMS"},"agent_actions":{"view_html":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX","download_json":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX.json","view_paper":"https://pith.science/paper/GOMHCDMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18110&json=true","fetch_graph":"https://pith.science/api/pith-number/GOMHCDMSONLZTYP7URERIXS6SX/graph.json","fetch_events":"https://pith.science/api/pith-number/GOMHCDMSONLZTYP7URERIXS6SX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX/action/storage_attestation","attest_author":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX/action/author_attestation","sign_citation":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX/action/citation_signature","submit_replication":"https://pith.science/pith/GOMHCDMSONLZTYP7URERIXS6SX/action/replication_record"}},"created_at":"2026-07-05T08:24:15.779119+00:00","updated_at":"2026-07-05T08:24:15.779119+00:00"}