{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AUVP5N7GYAPFMP3R4PDDX65ALJ","short_pith_number":"pith:AUVP5N7G","schema_version":"1.0","canonical_sha256":"052afeb7e6c01e563f71e3c63bfba05a5c51f3f0a4f6e5933ae80d302daa43a1","source":{"kind":"arxiv","id":"2203.10905","version":1},"attestation_state":"computed","paper":{"title":"Self-Imitation Learning from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksei Shpilman, Dmitry Ivanov, Georgiy Pshikhachev, Vladimir Egorov","submitted_at":"2022-03-21T11:56:56Z","abstract_excerpt":"Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD) remedies this issue by guiding the agent's exploration towards states experienced by an expert. Naturally, the benefits of this approach hinge on the quality of demonstrations, which are rarely optimal in realistic scenarios. Modern LfD algorithms require meticulous tuning of hyperparameters that control the influence of demonstrations and, as we show in the paper, struggle w"},"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":"2203.10905","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-21T11:56:56Z","cross_cats_sorted":[],"title_canon_sha256":"0d961cbddcdd0ab0d61a4f09f2f4eb32b73d98ccaea7797fd1d0c5f45fb8e13e","abstract_canon_sha256":"d5dcd66890e76729c79456615a1b03f50c6d73c1ddc38afbb1771a16b2015f78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:58.711559Z","signature_b64":"ILkj0df0Ydf8s3khRVWlbRvO4VqzfaYnwrYE+6k1aipH9E2ylS/Ww7OQOU0e5AXRULIHgFXTTCW+a43lgqpUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"052afeb7e6c01e563f71e3c63bfba05a5c51f3f0a4f6e5933ae80d302daa43a1","last_reissued_at":"2026-07-05T04:06:58.711138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:58.711138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Imitation Learning from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksei Shpilman, Dmitry Ivanov, Georgiy Pshikhachev, Vladimir Egorov","submitted_at":"2022-03-21T11:56:56Z","abstract_excerpt":"Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD) remedies this issue by guiding the agent's exploration towards states experienced by an expert. Naturally, the benefits of this approach hinge on the quality of demonstrations, which are rarely optimal in realistic scenarios. Modern LfD algorithms require meticulous tuning of hyperparameters that control the influence of demonstrations and, as we show in the paper, struggle w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10905","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/2203.10905/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":"2203.10905","created_at":"2026-07-05T04:06:58.711194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10905v1","created_at":"2026-07-05T04:06:58.711194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10905","created_at":"2026-07-05T04:06:58.711194+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUVP5N7GYAPF","created_at":"2026-07-05T04:06:58.711194+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUVP5N7GYAPFMP3R","created_at":"2026-07-05T04:06:58.711194+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUVP5N7G","created_at":"2026-07-05T04:06:58.711194+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/AUVP5N7GYAPFMP3R4PDDX65ALJ","json":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ.json","graph_json":"https://pith.science/api/pith-number/AUVP5N7GYAPFMP3R4PDDX65ALJ/graph.json","events_json":"https://pith.science/api/pith-number/AUVP5N7GYAPFMP3R4PDDX65ALJ/events.json","paper":"https://pith.science/paper/AUVP5N7G"},"agent_actions":{"view_html":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ","download_json":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ.json","view_paper":"https://pith.science/paper/AUVP5N7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10905&json=true","fetch_graph":"https://pith.science/api/pith-number/AUVP5N7GYAPFMP3R4PDDX65ALJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AUVP5N7GYAPFMP3R4PDDX65ALJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ/action/storage_attestation","attest_author":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ/action/author_attestation","sign_citation":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ/action/citation_signature","submit_replication":"https://pith.science/pith/AUVP5N7GYAPFMP3R4PDDX65ALJ/action/replication_record"}},"created_at":"2026-07-05T04:06:58.711194+00:00","updated_at":"2026-07-05T04:06:58.711194+00:00"}