{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O2VNFUCPHP55OI3YTGRL4Q7M32","short_pith_number":"pith:O2VNFUCP","schema_version":"1.0","canonical_sha256":"76aad2d04f3bfbd7237899a2be43ecdea3d235cac767d45d6461dc1b0ef8476a","source":{"kind":"arxiv","id":"2110.09796","version":1},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning with Value-based Episodic Memory","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Chongjie Zhang, Hao Hu, Jun Yang, Qianchuan Zhao, Qihan Liu, Xiaoteng Ma, Yiqin Yang","submitted_at":"2021-10-19T08:20:11Z","abstract_excerpt":"Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a different framework, which learns the V-function instead of the Q-function to naturally keep the learning procedure within the support of an offline dataset. To enable effective generalization while maintaining proper conservatism in offline learning, we propose Expectile V-Learning (EVL), which sm"},"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":"2110.09796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T08:20:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db7e3a793eb8c07629b6153164565d89fa10376cc10e8c4390b3e5feb7bf989b","abstract_canon_sha256":"54e14cd87c6c685aadb5d6a97eab7240b00c51e4be0e64228a686fc5dac706c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:59.251641Z","signature_b64":"aCtw3g2MbF8TaRcyEEpkPqYTfogKsfVBPLJrRMl4rT5l//+UtG6/uEr2kjvUYUBTcIDit18q/DuxG2TpOmdQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76aad2d04f3bfbd7237899a2be43ecdea3d235cac767d45d6461dc1b0ef8476a","last_reissued_at":"2026-07-05T03:23:59.251080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:59.251080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Value-based Episodic Memory","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Chongjie Zhang, Hao Hu, Jun Yang, Qianchuan Zhao, Qihan Liu, Xiaoteng Ma, Yiqin Yang","submitted_at":"2021-10-19T08:20:11Z","abstract_excerpt":"Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a different framework, which learns the V-function instead of the Q-function to naturally keep the learning procedure within the support of an offline dataset. To enable effective generalization while maintaining proper conservatism in offline learning, we propose Expectile V-Learning (EVL), which sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09796","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/2110.09796/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":"2110.09796","created_at":"2026-07-05T03:23:59.251141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09796v1","created_at":"2026-07-05T03:23:59.251141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09796","created_at":"2026-07-05T03:23:59.251141+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2VNFUCPHP55","created_at":"2026-07-05T03:23:59.251141+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2VNFUCPHP55OI3Y","created_at":"2026-07-05T03:23:59.251141+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2VNFUCP","created_at":"2026-07-05T03:23:59.251141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02349","citing_title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32","json":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32.json","graph_json":"https://pith.science/api/pith-number/O2VNFUCPHP55OI3YTGRL4Q7M32/graph.json","events_json":"https://pith.science/api/pith-number/O2VNFUCPHP55OI3YTGRL4Q7M32/events.json","paper":"https://pith.science/paper/O2VNFUCP"},"agent_actions":{"view_html":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32","download_json":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32.json","view_paper":"https://pith.science/paper/O2VNFUCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09796&json=true","fetch_graph":"https://pith.science/api/pith-number/O2VNFUCPHP55OI3YTGRL4Q7M32/graph.json","fetch_events":"https://pith.science/api/pith-number/O2VNFUCPHP55OI3YTGRL4Q7M32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32/action/storage_attestation","attest_author":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32/action/author_attestation","sign_citation":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32/action/citation_signature","submit_replication":"https://pith.science/pith/O2VNFUCPHP55OI3YTGRL4Q7M32/action/replication_record"}},"created_at":"2026-07-05T03:23:59.251141+00:00","updated_at":"2026-07-05T03:23:59.251141+00:00"}