{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PGZVFQTYG7IFDM7YXRVJZJYXRW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"878bf0151ccbacf047160c401e9575842a940c4d1f5937112da9912365071c91","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T11:45:08Z","title_canon_sha256":"9f2addac0b1d4ca284bcea507ee6e004adeee3833a4b536ed9eb09c7bbf72b06"},"schema_version":"1.0","source":{"id":"2101.11331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11331","created_at":"2026-07-05T02:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11331v2","created_at":"2026-07-05T02:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11331","created_at":"2026-07-05T02:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"PGZVFQTYG7IF","created_at":"2026-07-05T02:22:40Z"},{"alias_kind":"pith_short_16","alias_value":"PGZVFQTYG7IFDM7Y","created_at":"2026-07-05T02:22:40Z"},{"alias_kind":"pith_short_8","alias_value":"PGZVFQTY","created_at":"2026-07-05T02:22:40Z"}],"graph_snapshots":[{"event_id":"sha256:1e510f4749fb95883d36587fb8abced19f2643caf0c5d3775eccd1151c52f38a","target":"graph","created_at":"2026-07-05T02:22:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.11331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Philip J. Ball, Stephen J. Roberts","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T11:45:08Z","title":"OffCon$^3$: What is state of the art anyway?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11331","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1e8c252aa127c0696b9944e9cf42314f8fcc6e60c4992aba56b22b71447cad78","target":"record","created_at":"2026-07-05T02:22:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"878bf0151ccbacf047160c401e9575842a940c4d1f5937112da9912365071c91","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T11:45:08Z","title_canon_sha256":"9f2addac0b1d4ca284bcea507ee6e004adeee3833a4b536ed9eb09c7bbf72b06"},"schema_version":"1.0","source":{"id":"2101.11331","kind":"arxiv","version":2}},"canonical_sha256":"79b352c27837d051b3f8bc6a9ca7178da7d1f40c961cc6f807c8e47999a9d8f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79b352c27837d051b3f8bc6a9ca7178da7d1f40c961cc6f807c8e47999a9d8f0","first_computed_at":"2026-07-05T02:22:40.663378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:40.663378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jLOYCJ4AJo+1LHR0oXtf/dCNNuNOupcuVp84FR/ACe1DjdS2REok6rPaWsUyZa0zBiM0BtV7SKKBuX9mtp2eAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:40.663746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.11331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8c252aa127c0696b9944e9cf42314f8fcc6e60c4992aba56b22b71447cad78","sha256:1e510f4749fb95883d36587fb8abced19f2643caf0c5d3775eccd1151c52f38a"],"state_sha256":"61e28cc5ecff6473ec37b91777334d5db51ed60ae085c61f4bcb01d53adf716d"}