{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4YCTXJTAPV6EJDXEOQH7RH73EZ","short_pith_number":"pith:4YCTXJTA","schema_version":"1.0","canonical_sha256":"e6053ba6607d7c448ee4740ff89ffb267c65b3e3b9a77303a8a631c70b270ac4","source":{"kind":"arxiv","id":"2412.15517","version":1},"attestation_state":"computed","paper":{"title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafei Lyu, Jian Tao, Kai Yang, Yangkun Chen","submitted_at":"2024-12-20T03:09:18Z","abstract_excerpt":"Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments. However, the efficiency of these systems is often compromised by inadequate sample utilization and a lack of diversity in learning strategies. To enhance MARL performance, we introduce a novel sample reuse approach that dynamically adjusts policy updates based on observation novelty. Specifically, we employ a Random Network Distillation (RND) network to gauge the novelty of each agent's current state, assigning "},"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":"2412.15517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:09:18Z","cross_cats_sorted":[],"title_canon_sha256":"ffe63a7209fe3fdb8440a499ae10063bfb36e6af8efd1bb393be9e085746c753","abstract_canon_sha256":"794505920c219dc4586f62cb6f43e9367ae9b0c4ae3aa9f3b4a28bb91f4aec5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:24.595272Z","signature_b64":"uCiGv9/gslUlFHmXpNOoJSjcaPb3I01rDBv3uYrRQJg8r9SAQyRDg5WxYwkqD+ylZnAIx7pFXVxfWwHPca/MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6053ba6607d7c448ee4740ff89ffb267c65b3e3b9a77303a8a631c70b270ac4","last_reissued_at":"2026-07-05T09:52:24.594168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:24.594168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafei Lyu, Jian Tao, Kai Yang, Yangkun Chen","submitted_at":"2024-12-20T03:09:18Z","abstract_excerpt":"Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments. However, the efficiency of these systems is often compromised by inadequate sample utilization and a lack of diversity in learning strategies. To enhance MARL performance, we introduce a novel sample reuse approach that dynamically adjusts policy updates based on observation novelty. Specifically, we employ a Random Network Distillation (RND) network to gauge the novelty of each agent's current state, assigning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15517","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/2412.15517/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":"2412.15517","created_at":"2026-07-05T09:52:24.594865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15517v1","created_at":"2026-07-05T09:52:24.594865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15517","created_at":"2026-07-05T09:52:24.594865+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YCTXJTAPV6E","created_at":"2026-07-05T09:52:24.594865+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YCTXJTAPV6EJDXE","created_at":"2026-07-05T09:52:24.594865+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YCTXJTA","created_at":"2026-07-05T09:52:24.594865+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/4YCTXJTAPV6EJDXEOQH7RH73EZ","json":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ.json","graph_json":"https://pith.science/api/pith-number/4YCTXJTAPV6EJDXEOQH7RH73EZ/graph.json","events_json":"https://pith.science/api/pith-number/4YCTXJTAPV6EJDXEOQH7RH73EZ/events.json","paper":"https://pith.science/paper/4YCTXJTA"},"agent_actions":{"view_html":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ","download_json":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ.json","view_paper":"https://pith.science/paper/4YCTXJTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15517&json=true","fetch_graph":"https://pith.science/api/pith-number/4YCTXJTAPV6EJDXEOQH7RH73EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4YCTXJTAPV6EJDXEOQH7RH73EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ/action/storage_attestation","attest_author":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ/action/author_attestation","sign_citation":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ/action/citation_signature","submit_replication":"https://pith.science/pith/4YCTXJTAPV6EJDXEOQH7RH73EZ/action/replication_record"}},"created_at":"2026-07-05T09:52:24.594865+00:00","updated_at":"2026-07-05T09:52:24.594865+00:00"}