{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3G6RCQOPEERYE5KWOV5QU7KYRD","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":"a1c52874471ed2fc0fe4281b3f0fcdda5464c03287cd38430e62f6e91dd2dcf8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T21:45:03Z","title_canon_sha256":"7d48fc71f9b852b07f0ac9993f713319b68d4f0a8df299df30a66d9979b8a31f"},"schema_version":"1.0","source":{"id":"1905.00976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00976","created_at":"2026-07-05T01:41:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00976v2","created_at":"2026-07-05T01:41:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00976","created_at":"2026-07-05T01:41:47Z"},{"alias_kind":"pith_short_12","alias_value":"3G6RCQOPEERY","created_at":"2026-07-05T01:41:47Z"},{"alias_kind":"pith_short_16","alias_value":"3G6RCQOPEERYE5KW","created_at":"2026-07-05T01:41:47Z"},{"alias_kind":"pith_short_8","alias_value":"3G6RCQOP","created_at":"2026-07-05T01:41:47Z"}],"graph_snapshots":[{"event_id":"sha256:7bdc544af0ba39d7ba5cd8f3fc0a29aaab2bdd44511d7c07ce563a906bd9e823","target":"graph","created_at":"2026-07-05T01:41:47Z","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/1905.00976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of hyperparameters. One reason is that most approaches use a noisy version of their operating policy to explore - thereby limiting the range of exploration. In this paper, we introduce Collaborative Evolutionary Reinforcement Learning (CERL), a scalable framework that comprises a portfolio of policies that simultaneously explore and exploit diverse regions of the so","authors_text":"Evren Tumer, Kagan Tumer, Santiago Miret, Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Yinyin Liu, Zach Dwiel","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T21:45:03Z","title":"Collaborative Evolutionary Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00976","kind":"arxiv","version":2},"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":"sha256:542e9438107ed603e6bc9ad24fa789a523097850788a6bb4524f228e3d0e1ad1","target":"record","created_at":"2026-07-05T01:41:47Z","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":"a1c52874471ed2fc0fe4281b3f0fcdda5464c03287cd38430e62f6e91dd2dcf8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T21:45:03Z","title_canon_sha256":"7d48fc71f9b852b07f0ac9993f713319b68d4f0a8df299df30a66d9979b8a31f"},"schema_version":"1.0","source":{"id":"1905.00976","kind":"arxiv","version":2}},"canonical_sha256":"d9bd1141cf2123827556757b0a7d5888d1a85aa039df1eb9334ae2c0405ad949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9bd1141cf2123827556757b0a7d5888d1a85aa039df1eb9334ae2c0405ad949","first_computed_at":"2026-07-05T01:41:47.987565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:47.987565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZbBp85YhCO4gnosmMUKFTV71O7RfDof7H8pP1Ch5qUShtgkQKUIj03Y4aJ4QKb2DnwnDAtnUOvDPRZAohy4lAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:47.987949Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:542e9438107ed603e6bc9ad24fa789a523097850788a6bb4524f228e3d0e1ad1","sha256:7bdc544af0ba39d7ba5cd8f3fc0a29aaab2bdd44511d7c07ce563a906bd9e823"],"state_sha256":"a96aaf2ed29a3bb4f842ad774f77e53133b05ee32b9c03ab1d670785dd627f4a"}