{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O4E6ARILPMYLKYLXX56BJY3FYA","short_pith_number":"pith:O4E6ARIL","schema_version":"1.0","canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","source":{"kind":"arxiv","id":"2203.00822","version":1},"attestation_state":"computed","paper":{"title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shangdong Yang, Shuyang Liu, Wenbin Li, Xiao Liu, Yang Gao","submitted_at":"2022-03-02T02:18:48Z","abstract_excerpt":"Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies. To address this problem, we propose Boundary Characterization via the Minimum Experience Retention (BCMER), an end-to-end Interpretable Policy Distillation (IPD) framework. Unlike previous IPD approaches, BCMER distinguishes the importance of experiences and keeps a minimal but critical experience pool with almost no loss of policy similarity. Specifically, the proposed BCMER contains two basic steps. Fir"},"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":"2203.00822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86ccb9d016c182b4eaa9501b5b638af8914072443415fbcf8fad4ae11f0a5341","abstract_canon_sha256":"fcd06ca599793781ac7ea243042557234359ce959da59249fe83d1b642c9c343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:23.866042Z","signature_b64":"INQPhg1ajRLm4MsDD+YVIsZjTYPQ2XQSDelHBMhzX+/cp7nPNS4ODXGf8IRSqjff1Av0d/ZbdL57/9ta+5KxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","last_reissued_at":"2026-07-05T04:01:23.865501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:23.865501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shangdong Yang, Shuyang Liu, Wenbin Li, Xiao Liu, Yang Gao","submitted_at":"2022-03-02T02:18:48Z","abstract_excerpt":"Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies. To address this problem, we propose Boundary Characterization via the Minimum Experience Retention (BCMER), an end-to-end Interpretable Policy Distillation (IPD) framework. Unlike previous IPD approaches, BCMER distinguishes the importance of experiences and keeps a minimal but critical experience pool with almost no loss of policy similarity. Specifically, the proposed BCMER contains two basic steps. Fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00822","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/2203.00822/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":"2203.00822","created_at":"2026-07-05T04:01:23.865558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00822v1","created_at":"2026-07-05T04:01:23.865558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00822","created_at":"2026-07-05T04:01:23.865558+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4E6ARILPMYL","created_at":"2026-07-05T04:01:23.865558+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4E6ARILPMYLKYLX","created_at":"2026-07-05T04:01:23.865558+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4E6ARIL","created_at":"2026-07-05T04:01:23.865558+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/O4E6ARILPMYLKYLXX56BJY3FYA","json":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA.json","graph_json":"https://pith.science/api/pith-number/O4E6ARILPMYLKYLXX56BJY3FYA/graph.json","events_json":"https://pith.science/api/pith-number/O4E6ARILPMYLKYLXX56BJY3FYA/events.json","paper":"https://pith.science/paper/O4E6ARIL"},"agent_actions":{"view_html":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA","download_json":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA.json","view_paper":"https://pith.science/paper/O4E6ARIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00822&json=true","fetch_graph":"https://pith.science/api/pith-number/O4E6ARILPMYLKYLXX56BJY3FYA/graph.json","fetch_events":"https://pith.science/api/pith-number/O4E6ARILPMYLKYLXX56BJY3FYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/action/storage_attestation","attest_author":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/action/author_attestation","sign_citation":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/action/citation_signature","submit_replication":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/action/replication_record"}},"created_at":"2026-07-05T04:01:23.865558+00:00","updated_at":"2026-07-05T04:01:23.865558+00:00"}