{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MMYELEWYW5K35YGWPS3XBTSHQI","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":"2d18cc848552f499822c8f805014d030feaa80b89ce7881088466b0d960c6a31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T10:40:46Z","title_canon_sha256":"c58641b50b00525427c483c651672b38e57e453b26ba2dffe3711dce0aed60ab"},"schema_version":"1.0","source":{"id":"2311.00426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00426","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00426v1","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00426","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"MMYELEWYW5K3","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"MMYELEWYW5K35YGW","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"MMYELEWY","created_at":"2026-07-05T07:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:195361fb9d34f02098ceda6bc25972416d0f7d1b02052811a3e8f7acf2b8710a","target":"graph","created_at":"2026-07-05T07:07:57Z","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/2311.00426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration poses a fundamental challenge in Reinforcement Learning (RL) with sparse rewards, limiting an agent's ability to learn optimal decision-making due to a lack of informative feedback signals. Self-Imitation Learning (self-IL) has emerged as a promising approach for exploration, leveraging a replay buffer to store and reproduce successful behaviors. However, traditional self-IL methods, which rely on high-return transitions and assume singleton environments, face challenges in generalization, especially in procedurally-generated (PCG) environments. Therefore, new self-IL methods have ","authors_text":"Alain Andres, Daochen Zha, Javier Del Ser","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T10:40:46Z","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00426","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":"sha256:1b97da705bbe25866910ba07f5f9261df40ce4738ab2b95d11b71ffc342bb95b","target":"record","created_at":"2026-07-05T07:07:57Z","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":"2d18cc848552f499822c8f805014d030feaa80b89ce7881088466b0d960c6a31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T10:40:46Z","title_canon_sha256":"c58641b50b00525427c483c651672b38e57e453b26ba2dffe3711dce0aed60ab"},"schema_version":"1.0","source":{"id":"2311.00426","kind":"arxiv","version":1}},"canonical_sha256":"63304592d8b755bee0d67cb770ce47822b3be512a476ff3c7dae11e96fd59885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63304592d8b755bee0d67cb770ce47822b3be512a476ff3c7dae11e96fd59885","first_computed_at":"2026-07-05T07:07:57.574238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:57.574238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jxfQmRKr3yXWgFFgeerkOQ+fn+W17Lea7H7lkbZEPTr1D3oQ5Xu5k6FiR9k9wda6beZi+0pRiFD536UcMcrSCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:57.574751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b97da705bbe25866910ba07f5f9261df40ce4738ab2b95d11b71ffc342bb95b","sha256:195361fb9d34f02098ceda6bc25972416d0f7d1b02052811a3e8f7acf2b8710a"],"state_sha256":"0a91435d9ef1f7e46e5121951c4f6703ffe93fb4fce783086beeb00f7c13ba6e"}