{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QKFYNDVKWJSXYKLWEVPOHX2R5X","short_pith_number":"pith:QKFYNDVK","schema_version":"1.0","canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","source":{"kind":"arxiv","id":"2110.12628","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hai Nguyen, Zhihan Yang","submitted_at":"2021-10-25T04:08:57Z","abstract_excerpt":"When the environment is partially observable (PO), a deep reinforcement learning (RL) agent must learn a suitable temporal representation of the entire history in addition to a strategy to control. This problem is not novel, and there have been model-free and model-based algorithms proposed for this problem. However, inspired by recent success in model-free image-based RL, we noticed the absence of a model-free baseline for history-based RL that (1) uses full history and (2) incorporates recent advances in off-policy continuous control. Therefore, we implement recurrent versions of DDPG, TD3, "},"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":"2110.12628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1fc3ebab81d5ee5a36291d20f693decf389a40530759a5f811fc9abaa3ab0e0c","abstract_canon_sha256":"874f87b06e6a72dfcbba5040dabacd204f054fb0158594ad3784f3839bb8196f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:21.529799Z","signature_b64":"aOSPT8UG6R44RzVa8DNN9TV2gpSxENFgzOOuDUda5yEDDzGv2PgJ49Y3KJFPSU4U+3TXtBg42neo9ifriB6VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","last_reissued_at":"2026-07-05T03:26:21.529329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:21.529329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hai Nguyen, Zhihan Yang","submitted_at":"2021-10-25T04:08:57Z","abstract_excerpt":"When the environment is partially observable (PO), a deep reinforcement learning (RL) agent must learn a suitable temporal representation of the entire history in addition to a strategy to control. This problem is not novel, and there have been model-free and model-based algorithms proposed for this problem. However, inspired by recent success in model-free image-based RL, we noticed the absence of a model-free baseline for history-based RL that (1) uses full history and (2) incorporates recent advances in off-policy continuous control. Therefore, we implement recurrent versions of DDPG, TD3, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12628","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/2110.12628/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":"2110.12628","created_at":"2026-07-05T03:26:21.529382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12628v1","created_at":"2026-07-05T03:26:21.529382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12628","created_at":"2026-07-05T03:26:21.529382+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKFYNDVKWJSX","created_at":"2026-07-05T03:26:21.529382+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKFYNDVKWJSXYKLW","created_at":"2026-07-05T03:26:21.529382+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKFYNDVK","created_at":"2026-07-05T03:26:21.529382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.04341","citing_title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X","json":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X.json","graph_json":"https://pith.science/api/pith-number/QKFYNDVKWJSXYKLWEVPOHX2R5X/graph.json","events_json":"https://pith.science/api/pith-number/QKFYNDVKWJSXYKLWEVPOHX2R5X/events.json","paper":"https://pith.science/paper/QKFYNDVK"},"agent_actions":{"view_html":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X","download_json":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X.json","view_paper":"https://pith.science/paper/QKFYNDVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12628&json=true","fetch_graph":"https://pith.science/api/pith-number/QKFYNDVKWJSXYKLWEVPOHX2R5X/graph.json","fetch_events":"https://pith.science/api/pith-number/QKFYNDVKWJSXYKLWEVPOHX2R5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/action/storage_attestation","attest_author":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/action/author_attestation","sign_citation":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/action/citation_signature","submit_replication":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/action/replication_record"}},"created_at":"2026-07-05T03:26:21.529382+00:00","updated_at":"2026-07-05T03:26:21.529382+00:00"}