{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PGZVFQTYG7IFDM7YXRVJZJYXRW","short_pith_number":"pith:PGZVFQTY","schema_version":"1.0","canonical_sha256":"79b352c27837d051b3f8bc6a9ca7178da7d1f40c961cc6f807c8e47999a9d8f0","source":{"kind":"arxiv","id":"2101.11331","version":2},"attestation_state":"computed","paper":{"title":"OffCon$^3$: What is state of the art anyway?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Philip J. Ball, Stephen J. Roberts","submitted_at":"2021-01-27T11:45:08Z","abstract_excerpt":"Two popular approaches to model-free continuous control tasks are SAC and TD3. At first glance these approaches seem rather different; SAC aims to solve the entropy-augmented MDP by minimising the KL-divergence between a stochastic proposal policy and a hypotheical energy-basd soft Q-function policy, whereas TD3 is derived from DPG, which uses a deterministic policy to perform policy gradient ascent along the value function. In reality, both approaches are remarkably similar, and belong to a family of approaches we call `Off-Policy Continuous Generalized Policy Iteration'. This illuminates the"},"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":"2101.11331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T11:45:08Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"9f2addac0b1d4ca284bcea507ee6e004adeee3833a4b536ed9eb09c7bbf72b06","abstract_canon_sha256":"878bf0151ccbacf047160c401e9575842a940c4d1f5937112da9912365071c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:40.663746Z","signature_b64":"jLOYCJ4AJo+1LHR0oXtf/dCNNuNOupcuVp84FR/ACe1DjdS2REok6rPaWsUyZa0zBiM0BtV7SKKBuX9mtp2eAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79b352c27837d051b3f8bc6a9ca7178da7d1f40c961cc6f807c8e47999a9d8f0","last_reissued_at":"2026-07-05T02:22:40.663378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:40.663378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OffCon$^3$: What is state of the art anyway?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Philip J. Ball, Stephen J. Roberts","submitted_at":"2021-01-27T11:45:08Z","abstract_excerpt":"Two popular approaches to model-free continuous control tasks are SAC and TD3. At first glance these approaches seem rather different; SAC aims to solve the entropy-augmented MDP by minimising the KL-divergence between a stochastic proposal policy and a hypotheical energy-basd soft Q-function policy, whereas TD3 is derived from DPG, which uses a deterministic policy to perform policy gradient ascent along the value function. In reality, both approaches are remarkably similar, and belong to a family of approaches we call `Off-Policy Continuous Generalized Policy Iteration'. This illuminates the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11331","kind":"arxiv","version":2},"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/2101.11331/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":"2101.11331","created_at":"2026-07-05T02:22:40.663441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11331v2","created_at":"2026-07-05T02:22:40.663441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11331","created_at":"2026-07-05T02:22:40.663441+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGZVFQTYG7IF","created_at":"2026-07-05T02:22:40.663441+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGZVFQTYG7IFDM7Y","created_at":"2026-07-05T02:22:40.663441+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGZVFQTY","created_at":"2026-07-05T02:22:40.663441+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/PGZVFQTYG7IFDM7YXRVJZJYXRW","json":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW.json","graph_json":"https://pith.science/api/pith-number/PGZVFQTYG7IFDM7YXRVJZJYXRW/graph.json","events_json":"https://pith.science/api/pith-number/PGZVFQTYG7IFDM7YXRVJZJYXRW/events.json","paper":"https://pith.science/paper/PGZVFQTY"},"agent_actions":{"view_html":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW","download_json":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW.json","view_paper":"https://pith.science/paper/PGZVFQTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11331&json=true","fetch_graph":"https://pith.science/api/pith-number/PGZVFQTYG7IFDM7YXRVJZJYXRW/graph.json","fetch_events":"https://pith.science/api/pith-number/PGZVFQTYG7IFDM7YXRVJZJYXRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW/action/storage_attestation","attest_author":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW/action/author_attestation","sign_citation":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW/action/citation_signature","submit_replication":"https://pith.science/pith/PGZVFQTYG7IFDM7YXRVJZJYXRW/action/replication_record"}},"created_at":"2026-07-05T02:22:40.663441+00:00","updated_at":"2026-07-05T02:22:40.663441+00:00"}