{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NPFRXIYPRDIPVZAN4Q2QISM2KH","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":"3c7b466445816b00b0403a71ea07c227c5a959e32e18c7030a434164b2113d91","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T09:16:03Z","title_canon_sha256":"ddd03821a752fea93a9177bcc94bc5726932a7ad48b8210114e660b50d21ac97"},"schema_version":"1.0","source":{"id":"2201.02373","kind":"arxiv","version":11}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02373","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02373v11","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02373","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_12","alias_value":"NPFRXIYPRDIP","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_16","alias_value":"NPFRXIYPRDIPVZAN","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_8","alias_value":"NPFRXIYP","created_at":"2026-07-05T09:37:48Z"}],"graph_snapshots":[{"event_id":"sha256:6efcb95a5f7deb8782011ac60c688e0169c9ba4f7c7cefb4237e4e65c9107c68","target":"graph","created_at":"2026-07-05T09:37:48Z","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/2201.02373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms that strictly respect these theoretical frameworks have proven unscalable. Surprisingly, the only known scalable algorithms violate the GPI/TRL assumptions, e.g. due to required regularisation or other heuristics. The current explanation of their empirical success is essentially \"by analogy\": they are deemed approximate adaptations of theoretically sound methods. Unfortunately, studies have shown that in practice these ","authors_text":"Christian Schroeder de Witt, Jakob Foerster, Jakub Grudzien Kuba","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T09:16:03Z","title":"Mirror Learning: A Unifying Framework of Policy Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02373","kind":"arxiv","version":11},"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":"sha256:2c19e3ad9d40b09f900d5254d115a477dd278d855bfec509e1beba0d53e89c55","target":"record","created_at":"2026-07-05T09:37:48Z","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":"3c7b466445816b00b0403a71ea07c227c5a959e32e18c7030a434164b2113d91","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T09:16:03Z","title_canon_sha256":"ddd03821a752fea93a9177bcc94bc5726932a7ad48b8210114e660b50d21ac97"},"schema_version":"1.0","source":{"id":"2201.02373","kind":"arxiv","version":11}},"canonical_sha256":"6bcb1ba30f88d0fae40de43504499a51cf4c4b844c85e6ccc36b8d9a8e188435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bcb1ba30f88d0fae40de43504499a51cf4c4b844c85e6ccc36b8d9a8e188435","first_computed_at":"2026-07-05T09:37:48.179972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:48.179972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UxAbexDQuPSAfmpvdxSjpCUZngGOLzxJma9f+haudr6Y121Cm879bXJEiOD1ox7omekAlCGQj96ulQeJWAiPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:48.180480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02373","source_kind":"arxiv","source_version":11}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c19e3ad9d40b09f900d5254d115a477dd278d855bfec509e1beba0d53e89c55","sha256:6efcb95a5f7deb8782011ac60c688e0169c9ba4f7c7cefb4237e4e65c9107c68"],"state_sha256":"5021ab990566f6be74293c00deb5556379ba37a47ee44251101671e339990ea1"}