{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GAII563MHLV6DS43WPPDAU3B3V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f851b3c6b9b54bb2a905ff08298c75d4b6ef19dd2c952b744865e339e24b6518","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-19T05:27:48Z","title_canon_sha256":"5fe7f73149c9c6121ac18c61f9dd982a5922c309d863d1e8cfed00954f7ecf57"},"schema_version":"1.0","source":{"id":"2308.09909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09909","created_at":"2026-07-05T06:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09909v1","created_at":"2026-07-05T06:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09909","created_at":"2026-07-05T06:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"GAII563MHLV6","created_at":"2026-07-05T06:42:48Z"},{"alias_kind":"pith_short_16","alias_value":"GAII563MHLV6DS43","created_at":"2026-07-05T06:42:48Z"},{"alias_kind":"pith_short_8","alias_value":"GAII563M","created_at":"2026-07-05T06:42:48Z"}],"graph_snapshots":[{"event_id":"sha256:a8bad19364a837d30be686c764ba244592a443d9b6680d9426631124eaf83459","target":"graph","created_at":"2026-07-05T06:42:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.09909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration. While the computation of many intrinsic rewards relies on estimating variational posteriors using neural network approximators, a notable challenge has surfaced due to the limited expressive capability of these neural statistics approximators. We pinpoint this challenge as the \"revisitation\" issue, where agents recurrently explore confined areas of the task space. To combat this, we propose a dynamic reward scaling approach. This method is crafted to stabilize the significa","authors_text":"Chenghao Li, Chongjie Zhang, Qianchuan Zhao, Tonghan Wang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-19T05:27:48Z","title":"Never Explore Repeatedly in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09909","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:53dd3f6e815e45591371a6d978a816f7e645ed702f1bf38fc1537685727cad6a","target":"record","created_at":"2026-07-05T06:42:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f851b3c6b9b54bb2a905ff08298c75d4b6ef19dd2c952b744865e339e24b6518","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-19T05:27:48Z","title_canon_sha256":"5fe7f73149c9c6121ac18c61f9dd982a5922c309d863d1e8cfed00954f7ecf57"},"schema_version":"1.0","source":{"id":"2308.09909","kind":"arxiv","version":1}},"canonical_sha256":"30108efb6c3aebe1cb9bb3de305361dd5878da99ce5ef902fceea4a98f77bc5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30108efb6c3aebe1cb9bb3de305361dd5878da99ce5ef902fceea4a98f77bc5f","first_computed_at":"2026-07-05T06:42:48.439624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:48.439624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TwUcUQ1MEA2/8T9uigGHlILqLvkj8eHC9Hz+CP7X06gofVfQEHT2QBqksh3771u8NnM2Tg0ZSoP9qUeEwlJODA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:48.440096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53dd3f6e815e45591371a6d978a816f7e645ed702f1bf38fc1537685727cad6a","sha256:a8bad19364a837d30be686c764ba244592a443d9b6680d9426631124eaf83459"],"state_sha256":"46299ce1a726f929777421f39e19b79d8463652d8648059ef91dd19db0f67026"}