{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I3K74Q2DJSDNFBHSS47TUEBQTE","short_pith_number":"pith:I3K74Q2D","schema_version":"1.0","canonical_sha256":"46d5fe43434c86d284f2973f3a1030993491686c851e85bec56a4990a270a672","source":{"kind":"arxiv","id":"2103.17258","version":3},"attestation_state":"computed","paper":{"title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiroki Furuta, Shixiang Shane Gu, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo","submitted_at":"2021-03-31T17:55:20Z","abstract_excerpt":"Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While they have clear algorithmic distinctions, they also have many implementation differences that are algorithm-independent and sometimes under-emphasized. Such mixing of algorithmic novelty and implementation craftsmanship makes rigorous analyses of the sources of performance improvements across algorithms difficult. In this work, we focus on a series of off-policy inference-based actor-critic algorithms -- MPO, AWR, and SAC -- to decouple their algorithmic innovations and implementation decis"},"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":"2103.17258","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-31T17:55:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3217ab7a692f7b3cbf4f2384c380577e19fa8b17e48b7062b68d304b8f59c3f2","abstract_canon_sha256":"86020bad8e038eb57e873a516c2ca1972b7e6f8c62442a260ef9d5b966a91ff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:13.098581Z","signature_b64":"VsrYOcse/xUFIk6xado2KAElEhbkE7JKN80aq0gktVUCda6TSTZ181go9F0vcKVhZeaQ+8uXg4mrYqQf9s/nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d5fe43434c86d284f2973f3a1030993491686c851e85bec56a4990a270a672","last_reissued_at":"2026-07-05T03:25:13.098096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:13.098096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiroki Furuta, Shixiang Shane Gu, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo","submitted_at":"2021-03-31T17:55:20Z","abstract_excerpt":"Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While they have clear algorithmic distinctions, they also have many implementation differences that are algorithm-independent and sometimes under-emphasized. Such mixing of algorithmic novelty and implementation craftsmanship makes rigorous analyses of the sources of performance improvements across algorithms difficult. In this work, we focus on a series of off-policy inference-based actor-critic algorithms -- MPO, AWR, and SAC -- to decouple their algorithmic innovations and implementation decis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17258","kind":"arxiv","version":3},"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/2103.17258/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":"2103.17258","created_at":"2026-07-05T03:25:13.098153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.17258v3","created_at":"2026-07-05T03:25:13.098153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17258","created_at":"2026-07-05T03:25:13.098153+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3K74Q2DJSDN","created_at":"2026-07-05T03:25:13.098153+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3K74Q2DJSDNFBHS","created_at":"2026-07-05T03:25:13.098153+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3K74Q2D","created_at":"2026-07-05T03:25:13.098153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08803","citing_title":"Some Essential Constructive Foundations for Systems and Control","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE","json":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE.json","graph_json":"https://pith.science/api/pith-number/I3K74Q2DJSDNFBHSS47TUEBQTE/graph.json","events_json":"https://pith.science/api/pith-number/I3K74Q2DJSDNFBHSS47TUEBQTE/events.json","paper":"https://pith.science/paper/I3K74Q2D"},"agent_actions":{"view_html":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE","download_json":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE.json","view_paper":"https://pith.science/paper/I3K74Q2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.17258&json=true","fetch_graph":"https://pith.science/api/pith-number/I3K74Q2DJSDNFBHSS47TUEBQTE/graph.json","fetch_events":"https://pith.science/api/pith-number/I3K74Q2DJSDNFBHSS47TUEBQTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE/action/storage_attestation","attest_author":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE/action/author_attestation","sign_citation":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE/action/citation_signature","submit_replication":"https://pith.science/pith/I3K74Q2DJSDNFBHSS47TUEBQTE/action/replication_record"}},"created_at":"2026-07-05T03:25:13.098153+00:00","updated_at":"2026-07-05T03:25:13.098153+00:00"}