{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I3K74Q2DJSDNFBHSS47TUEBQTE","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":"86020bad8e038eb57e873a516c2ca1972b7e6f8c62442a260ef9d5b966a91ff1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-31T17:55:20Z","title_canon_sha256":"3217ab7a692f7b3cbf4f2384c380577e19fa8b17e48b7062b68d304b8f59c3f2"},"schema_version":"1.0","source":{"id":"2103.17258","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.17258","created_at":"2026-07-05T03:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2103.17258v3","created_at":"2026-07-05T03:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17258","created_at":"2026-07-05T03:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"I3K74Q2DJSDN","created_at":"2026-07-05T03:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"I3K74Q2DJSDNFBHS","created_at":"2026-07-05T03:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"I3K74Q2D","created_at":"2026-07-05T03:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:265ef6445d191c60ce9a622b7bd5314435775c2e8a32cdf8c304d050425dd9e6","target":"graph","created_at":"2026-07-05T03:25:13Z","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/2103.17258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hiroki Furuta, Shixiang Shane Gu, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-31T17:55:20Z","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17258","kind":"arxiv","version":3},"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:b3b5a4b7b797c093b2327f7e9469ab766c6dbb6d3570140f0639fb20cd2a39ee","target":"record","created_at":"2026-07-05T03:25:13Z","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":"86020bad8e038eb57e873a516c2ca1972b7e6f8c62442a260ef9d5b966a91ff1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-31T17:55:20Z","title_canon_sha256":"3217ab7a692f7b3cbf4f2384c380577e19fa8b17e48b7062b68d304b8f59c3f2"},"schema_version":"1.0","source":{"id":"2103.17258","kind":"arxiv","version":3}},"canonical_sha256":"46d5fe43434c86d284f2973f3a1030993491686c851e85bec56a4990a270a672","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46d5fe43434c86d284f2973f3a1030993491686c851e85bec56a4990a270a672","first_computed_at":"2026-07-05T03:25:13.098096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:13.098096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VsrYOcse/xUFIk6xado2KAElEhbkE7JKN80aq0gktVUCda6TSTZ181go9F0vcKVhZeaQ+8uXg4mrYqQf9s/nBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:13.098581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.17258","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3b5a4b7b797c093b2327f7e9469ab766c6dbb6d3570140f0639fb20cd2a39ee","sha256:265ef6445d191c60ce9a622b7bd5314435775c2e8a32cdf8c304d050425dd9e6"],"state_sha256":"ab5c910a1a825d76f0d4e6c88f7cb836790773b751040bc8b836a884e639f2ac"}